Triple

T15078643
Position Surface form Disambiguated ID Type / Status
Subject Lisa Banes E380075 entity
Predicate familyName P18 FINISHED
Object Banes
Banes is the surname of American stage, film, and television actress Lisa Banes, known for her work in productions such as "Gone Girl" and "Cocktail."
 E1135168 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: Banes | Statement: [Lisa Banes, familyName, Banes]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Banes
Context triple: [Lisa Banes, familyName, Banes]
  • A. Banes
    Banes is a coastal municipality in eastern Cuba’s Holguín Province, historically known for its sugar industry and archaeological sites.
  • B. Baralbins
    Baralbins are the inhabitants of the French commune of Bar-sur-Aube in the Grand Est region of northeastern France.
  • C. Bannik
    Bannik is a bathhouse-dwelling spirit in Slavic mythology, known for guarding the banya and sometimes scalding or frightening those who disrespect it.
  • D. Bann
    Bann is an alternative name for the River Bann, one of the longest and most significant rivers in Northern Ireland.
  • E. Gaddanes
    Gaddanes is an alternative name for the Gaddang language, an Austronesian language spoken by the Gaddang people of northern Luzon in the Philippines.
  • 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: Banes
Triple: [Lisa Banes, familyName, Banes]
Generated description
Banes is the surname of American stage, film, and television actress Lisa Banes, known for her work in productions such as "Gone Girl" and "Cocktail."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Banes
Target entity description: Banes is the surname of American stage, film, and television actress Lisa Banes, known for her work in productions such as "Gone Girl" and "Cocktail."
  • A. Banes
    Banes is a coastal municipality in eastern Cuba’s Holguín Province, historically known for its sugar industry and archaeological sites.
  • B. Baralbins
    Baralbins are the inhabitants of the French commune of Bar-sur-Aube in the Grand Est region of northeastern France.
  • C. Bannik
    Bannik is a bathhouse-dwelling spirit in Slavic mythology, known for guarding the banya and sometimes scalding or frightening those who disrespect it.
  • D. Bann
    Bann is an alternative name for the River Bann, one of the longest and most significant rivers in Northern Ireland.
  • E. Gaddanes
    Gaddanes is an alternative name for the Gaddang language, an Austronesian language spoken by the Gaddang people of northern Luzon in the Philippines.
  • 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_69d85cd7683881908d405c1b5d7b4f7f completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69dff7fe5a208190823900b25e298dab completed April 15, 2026, 8:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69fea5d4f6a48190aeb42341b0c395a7 completed May 9, 2026, 3:11 a.m.
NEDg Description generation batch_69fea65a34f08190a76965dfee5b89e5 completed May 9, 2026, 3:13 a.m.
NED2 Entity disambiguation (via description) batch_69fea6e097bc81909ba468de2673b22e completed May 9, 2026, 3:15 a.m.
Created at: April 10, 2026, 3:03 a.m.