Triple

T3930670
Position Surface form Disambiguated ID Type / Status
Subject Caesarea in Cappadocia E93385 entity
Predicate ancientName P2834 FINISHED
Object Mazaca
Mazaca was an ancient city in central Anatolia that later became known as Caesarea in Cappadocia, an important regional center in Hellenistic and Roman times.
 E399397 NE FINISHED

How this triple was built (4 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: Mazaca | Statement: [Caesarea in Cappadocia, ancientName, Mazaca]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mazaca
Context triple: [Caesarea in Cappadocia, ancientName, Mazaca]
  • A. Macua
    Macua is an alternative name for Makhuwa, a major Bantu ethnic group and language community primarily found in northern Mozambique.
  • B. Zapote
    Zapote is a district of San José, Costa Rica, known for housing important government buildings and urban residential areas.
  • C. Naranjal
    Naranjal is a town and canton in southwestern Ecuador known for its agricultural production and location within Guayas Province.
  • D. Matucana
    Matucana is a small Andean town in Peru that serves as the capital of Huarochirí Province in the Lima Region.
  • E. Jipijapa
    Jipijapa is a city in coastal Ecuador known historically for its production of Panama hats and its agricultural economy.
  • 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: Mazaca
Triple: [Caesarea in Cappadocia, ancientName, Mazaca]
Generated description
Mazaca was an ancient city in central Anatolia that later became known as Caesarea in Cappadocia, an important regional center in Hellenistic and Roman times.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mazaca
Target entity description: Mazaca was an ancient city in central Anatolia that later became known as Caesarea in Cappadocia, an important regional center in Hellenistic and Roman times.
  • A. Macua
    Macua is an alternative name for Makhuwa, a major Bantu ethnic group and language community primarily found in northern Mozambique.
  • B. Zapote
    Zapote is a district of San José, Costa Rica, known for housing important government buildings and urban residential areas.
  • C. Naranjal
    Naranjal is a town and canton in southwestern Ecuador known for its agricultural production and location within Guayas Province.
  • D. Matucana
    Matucana is a small Andean town in Peru that serves as the capital of Huarochirí Province in the Lima Region.
  • E. Jipijapa
    Jipijapa is a city in coastal Ecuador known historically for its production of Panama hats and its agricultural economy.
  • F. None of above. chosen

Provenance (5 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_69aed96bfa1081908f7b30f2c647dee6 completed March 9, 2026, 2:30 p.m.
NER Named-entity recognition batch_69aeeda7cf3c81909df30744bddbad7e completed March 9, 2026, 3:56 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5288408f0819090217513e7a21091 completed March 14, 2026, 9:21 a.m.
NEDg Description generation batch_69b5294a9b80819083124bc2ff6828aa completed March 14, 2026, 9:24 a.m.
NED2 Entity disambiguation (via description) batch_69b529f6a3488190a7a9ae37f71cff56 completed March 14, 2026, 9:27 a.m.
Created at: March 9, 2026, 3:23 p.m.