Triple

T15912786
Position Surface form Disambiguated ID Type / Status
Subject Signetics E385888 entity
Predicate hasFounder P104 FINISHED
Object David Allison E385888 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 Allison | Statement: [Signetics, hasFounder, David Allison]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: David Allison
Context triple: [Signetics, hasFounder, David Allison]
  • A. David Allison chosen
    David Allison is a technology entrepreneur best known as one of the founders of the early semiconductor company Signetics.
  • B. David Carl Allison
    David Carl Allison was an American NASCAR driver best known as a rising star in the late 1980s and early 1990s before his career was tragically cut short by a helicopter crash.
  • C. Ian Allison
    Ian Allison is a Canadian sports executive best known for his leadership role as chairman of professional soccer club Cavalry FC.
  • D. Ian Dunn
    Ian Dunn is a British actor known for his work in television, film, and theatre, and for being married to the late actress Emma Chambers.
  • E. Daniel Christopher Allison
    Daniel Christopher Allison is an American orthopedic surgeon best known as the husband of actress Monica Potter.
  • 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_69d86da686e4819097cbf3b1fc2d881d completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e156601c988190b9bd0cd75897651b completed April 16, 2026, 9:36 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffcf11fd1481909f460cfa4485d3e3 completed May 10, 2026, 12:19 a.m.
Created at: April 10, 2026, 4:52 a.m.