Triple

T21911275
Position Surface form Disambiguated ID Type / Status
Subject Marvin Hagler E541068 entity
Predicate familyName P18 FINISHED
Object Hagler NE NERFINISHED

How this triple was built (2 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: Hagler | Statement: [Marvin Hagler, familyName, Hagler]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hagler
Context triple: [Marvin Hagler, familyName, Hagler]
  • A. Hagler chosen
    Hagler is the surname of Marvin Hagler, the legendary American middleweight boxing champion.
  • B. Henry Hager
    Henry Hager is an American businessman and former White House aide who is married to Jenna Bush Hager, the daughter of former U.S. President George W. Bush.
  • C. Frazier
    Frazier is a common English-language surname of Scottish and Irish origin, borne by various notable figures in sports, entertainment, and public life.
  • D. Henry Harold "Hal" Hager
    Henry Harold "Hal" Hager is the youngest son of television personality and author Jenna Bush Hager and her husband Henry Hager.
  • E. Paul Hager
    Paul Hager is a relatively obscure individual whose primary public mention appears to be as a namesake in reference data, with no widely documented achievements or biography.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0c47c4b9c8190a5586a75f5f36453 completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f121da36e88190b42b82641ec54a19 completed April 28, 2026, 9:08 p.m.
Created at: April 16, 2026, 7:40 p.m.