Triple

T13431180
Position Surface form Disambiguated ID Type / Status
Subject David Green E313613 entity
Predicate name P16 FINISHED
Object David Green E313613 NE FINISHED

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: David Green | Statement: [David Green, name, David Green]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: David Green
Context triple: [David Green, name, David Green]
  • A. David Green chosen
    David Green is an American businessman and philanthropist best known as the founder of the arts-and-crafts retail chain Hobby Lobby.
  • B. David M. Green
    David M. Green is a distinguished figure in the field of acoustics recognized for his significant contributions with the prestigious ASA Gold Medal.
  • C. David Greene
    David Greene was a British-born film and television director known for his work on acclaimed TV movies and miniseries from the 1960s through the 1990s.
  • D. David Gest
    David Gest was an American television personality and music producer best known for his high-profile marriage to entertainer Liza Minnelli and his appearances on British reality TV.
  • E. Jay Graydon
    Jay Graydon is an American guitarist, songwriter, and Grammy-winning producer known for his sophisticated pop and jazz fusion work with artists such as Steely Dan, Al Jarreau, and Airplay.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d806ad0c44819088833ae1ec9e9690 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69dbaed41a5481908800033303224adb completed April 12, 2026, 2:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69f7398b828c8190a029a5862ae1fded completed May 3, 2026, 12:03 p.m.
Created at: April 9, 2026, 9:40 p.m.