Triple

T6230679
Position Surface form Disambiguated ID Type / Status
Subject Esther Williams E139343 entity
Predicate spouse P13 FINISHED
Object Ben Gage
Ben Gage was an American radio announcer and actor best known for his work in radio drama and for being married to swimming and film star Esther Williams.
E578106 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: Ben Gage | Statement: [Esther Williams, spouse, Ben Gage]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ben Gage
Context triple: [Esther Williams, spouse, Ben Gage]
  • A. Don Galloway
    Don Galloway was an American actor best known for his role as Detective Sergeant Ed Brown on the television series "Ironside."
  • B. Leo Gordon
    Leo Gordon was an American character actor and screenwriter known for his tough-guy roles in numerous Westerns and crime films from the 1950s through the 1970s.
  • C. Frank Magee
    Frank Magee is an editor known for his work on the horror film "The Beast with Five Fingers."
  • D. Jack R. Gage
    Jack R. Gage was an American politician who served as the 25th governor of Wyoming in the early 1960s.
  • E. Alexander Gann
    Alexander Gann is a molecular biologist and science editor known for his work on genetics and for co-authoring influential textbooks in molecular biology.
  • 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: Ben Gage
Triple: [Esther Williams, spouse, Ben Gage]
Generated description
Ben Gage was an American radio announcer and actor best known for his work in radio drama and for being married to swimming and film star Esther Williams.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Ben Gage
Target entity description: Ben Gage was an American radio announcer and actor best known for his work in radio drama and for being married to swimming and film star Esther Williams.
  • A. Don Galloway
    Don Galloway was an American actor best known for his role as Detective Sergeant Ed Brown on the television series "Ironside."
  • B. Leo Gordon
    Leo Gordon was an American character actor and screenwriter known for his tough-guy roles in numerous Westerns and crime films from the 1950s through the 1970s.
  • C. Frank Magee
    Frank Magee is an editor known for his work on the horror film "The Beast with Five Fingers."
  • D. Jack R. Gage
    Jack R. Gage was an American politician who served as the 25th governor of Wyoming in the early 1960s.
  • E. Alexander Gann
    Alexander Gann is a molecular biologist and science editor known for his work on genetics and for co-authoring influential textbooks in molecular biology.
  • 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_69c008afd3148190b71e9eaa60420dd1 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c062ec5be4819084d6df2e8dd2a542 completed March 22, 2026, 9:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69c20de90ba08190be1e0c44b5b13f53 completed March 24, 2026, 4:07 a.m.
NEDg Description generation batch_69c212d46f648190b72eb440d02178b8 completed March 24, 2026, 4:28 a.m.
NED2 Entity disambiguation (via description) batch_69c2138541608190a3ea346ff23974a3 completed March 24, 2026, 4:31 a.m.
Created at: March 22, 2026, 4:22 p.m.