Triple

T2142911
Position Surface form Disambiguated ID Type / Status
Subject Coco E46999 entity
Predicate storyBy P1955 FINISHED
Object Matthew Aldrich E314016 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: Matthew Aldrich | Statement: [Coco, storyBy, Matthew Aldrich]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Matthew Aldrich
Context triple: [Coco, storyBy, Matthew Aldrich]
  • A. Matthew Aldrich chosen
    Matthew Aldrich is an American screenwriter best known for co-writing Pixar’s Academy Award–winning animated film "Coco."
  • B. Matthew Robbins
    Matthew Robbins is an American screenwriter and filmmaker known for his work on genre films such as Crimson Peak, Dragonslayer, and collaborations with directors like Guillermo del Toro.
  • C. Matthew Holworthy
    Matthew Holworthy was a 17th-century English merchant and philanthropist best known for endowing the Holworthy Professorship of English Law at the University of Cambridge.
  • D. Matthew Elliott
    Matthew Elliott is a British political strategist and campaigner best known for leading the pro-Brexit Vote Leave campaign.
  • E. Christian Ross
    Christian Ross was the wife of Scottish poet Allan Ramsay, known primarily through her connection to the influential 18th-century literary figure.
  • 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_69a88a1933e0819094f18426ed74180f completed March 4, 2026, 7:38 p.m.
NER Named-entity recognition batch_69abbe206db0819095772af5358dca55 completed March 7, 2026, 5:56 a.m.
NED1 Entity disambiguation (via context triple) batch_69b12de0989481909ce71f3fb739ac2a completed March 11, 2026, 8:54 a.m.
Created at: March 4, 2026, 7:44 p.m.