Triple

T10534742
Position Surface form Disambiguated ID Type / Status
Subject Dos Pilas E248533 entity
Predicate archaeologicalProject P31090 FINISHED
Object Petexbatún Archaeological Project
The Petexbatún Archaeological Project is a major research initiative focused on investigating the ancient Maya cities and political dynamics of the Petexbatún region in Guatemala.
E868675 NE FINISHED

How this triple was built (5 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Petexbatún Archaeological Project | Statement: [Dos Pilas, archaeologicalProject, Petexbatún Archaeological Project]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Petexbatún Archaeological Project
Context triple: [Dos Pilas, archaeologicalProject, Petexbatún Archaeological Project]
  • A. University of Pennsylvania Tikal Project
    The University of Pennsylvania Tikal Project was a major mid-20th-century archaeological research initiative that conducted extensive excavations and documentation at the ancient Maya city of Tikal in Guatemala.
  • B. Tumaco-La Tolita archaeological tradition
    The Tumaco-La Tolita archaeological tradition was a pre-Columbian culture of the Pacific coast of present-day Colombia and Ecuador, renowned for its sophisticated goldwork, ceramics, and complex ceremonial practices.
  • C. Olmecas de Tabasco
    Olmecas de Tabasco is a professional baseball team from the Mexican state of Tabasco that competes in the Mexican League.
  • D. Atzompa archaeological site
    The Atzompa archaeological site is a pre-Hispanic Zapotec settlement and satellite center of Monte Albán located in the Oaxaca Valley of southern Mexico.
  • E. Tres Zapotes
    Tres Zapotes is an important pre-Columbian archaeological site in Veracruz, Mexico, known for its monumental stone sculptures and as a key center of the Olmec and later Epi-Olmec cultures.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Petexbatún Archaeological Project
Triple: [Dos Pilas, archaeologicalProject, Petexbatún Archaeological Project]
Generated description
The Petexbatún Archaeological Project is a major research initiative focused on investigating the ancient Maya cities and political dynamics of the Petexbatún region in Guatemala.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Petexbatún Archaeological Project
Target entity description: The Petexbatún Archaeological Project is a major research initiative focused on investigating the ancient Maya cities and political dynamics of the Petexbatún region in Guatemala.
  • A. University of Pennsylvania Tikal Project
    The University of Pennsylvania Tikal Project was a major mid-20th-century archaeological research initiative that conducted extensive excavations and documentation at the ancient Maya city of Tikal in Guatemala.
  • B. Tumaco-La Tolita archaeological tradition
    The Tumaco-La Tolita archaeological tradition was a pre-Columbian culture of the Pacific coast of present-day Colombia and Ecuador, renowned for its sophisticated goldwork, ceramics, and complex ceremonial practices.
  • C. Olmecas de Tabasco
    Olmecas de Tabasco is a professional baseball team from the Mexican state of Tabasco that competes in the Mexican League.
  • D. Atzompa archaeological site
    The Atzompa archaeological site is a pre-Hispanic Zapotec settlement and satellite center of Monte Albán located in the Oaxaca Valley of southern Mexico.
  • E. Tres Zapotes
    Tres Zapotes is an important pre-Columbian archaeological site in Veracruz, Mexico, known for its monumental stone sculptures and as a key center of the Olmec and later Epi-Olmec cultures.
  • F. None of above. chosen
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: archaeologicalProject
Context triple: [Dos Pilas, archaeologicalProject, Petexbatún Archaeological Project]
  • A. hasArchaeologicalProject chosen
    Indicates that an entity is associated with or involved in a specific archaeological project.
  • B. archaeologicalExcavations
    Indicates that archaeological excavations have been carried out on or are associated with the subject, typically involving systematic digging and recovery of material remains.
  • C. archaeologicalDiscipline
    Indicates that one entity is an archaeological field or subfield in which the other entity (such as a person, project, or work) is specialized or involved.
  • D. archaeologyAt
    Indicates that an archaeological activity, study, or investigation is conducted at a specific location or site.
  • E. archaeologicalPhase
    Indicates the specific archaeological phase or period to which an object, feature, or context is assigned within a stratigraphic or chronological sequence.
  • F. None of above.

Provenance (6 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d381c5c7448190bec34bee7ec72bac completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d50a1a754c8190b53f2df28a1dfef1 completed April 7, 2026, 1:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69d90e507b408190ae3538d02536ef4c completed April 10, 2026, 2:50 p.m.
NEDg Description generation batch_69d91233a5d081908a8c9f6a3177f40e completed April 10, 2026, 3:07 p.m.
NED2 Entity disambiguation (via description) batch_69d912d18d2081909a6ebce1af1fb96a completed April 10, 2026, 3:10 p.m.
PD Predicate disambiguation batch_69d4fb9729288190a0149f127acd7ae3 completed April 7, 2026, 12:41 p.m.
Created at: April 6, 2026, 12:31 p.m.