Triple

T1806022
Position Surface form Disambiguated ID Type / Status
Subject Gia Zavala Damon E40220 entity
Predicate sibling P363 FINISHED
Object Isabella Damon E54939 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: Isabella Damon | Statement: [Gia Zavala Damon, sibling, Isabella Damon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Isabella Damon
Context triple: [Gia Zavala Damon, sibling, Isabella Damon]
  • A. Isabella Damon chosen
    Isabella Damon is one of American actor Matt Damon's daughters, known primarily for being part of his private family life.
  • B. Isabella Strahan
    Isabella Strahan is an American college student and model best known as the daughter of former NFL star and television personality Michael Strahan.
  • C. Annabella Stewart
    Annabella Stewart was a medieval Scottish princess, the daughter of King James I of Scotland.
  • D. Anabella Drummond
    Anabella Drummond was a 14th-century Scottish queen consort, noted for her political influence and as the wife of King Robert III of Scotland.
  • E. Sophie Devereaux
    Sophie Devereaux is a sophisticated grifter and master of disguise who serves as the team's con artist in the television series "Leverage."
  • 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_69a88643a3388190a612f2ebe1fb29e7 completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69aa659798b88190bd3070349ce6bebb completed March 6, 2026, 5:26 a.m.
NED1 Entity disambiguation (via context triple) batch_69adb5df20948190943a60c209270b62 completed March 8, 2026, 5:46 p.m.
Created at: March 4, 2026, 7:32 p.m.