Triple

T14239018
Position Surface form Disambiguated ID Type / Status
Subject Captain Mike Yates E352958 entity
Predicate worksWith P398 FINISHED
Object Jo Grant E352947 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: Jo Grant | Statement: [Captain Mike Yates, worksWith, Jo Grant]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jo Grant
Context triple: [Captain Mike Yates, worksWith, Jo Grant]
  • A. Jo Grant chosen
    Jo Grant is a spirited and resourceful companion of the Third Doctor in the classic British science fiction series Doctor Who.
  • B. Diana Prince
    Diana Prince is the Amazonian warrior princess better known as Wonder Woman, a DC Comics superhero who leaves her hidden island to protect humanity.
  • C. Valeria Richards
    Valeria Richards is a highly intelligent Marvel Comics character, the daughter of Reed Richards and Sue Storm, often depicted as a child prodigy whose genius rivals that of her father.
  • D. Kara Danvers
    Kara Danvers is the civilian identity of Supergirl, a Kryptonian superhero and central protagonist in the Arrowverse television franchise.
  • E. Mary Marston
    Mary Marston was the wife of Samuel Osgood, an early American political figure and the first U.S. Postmaster General.
  • 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_69d8278adc7c8190a9218d69bce3c4e6 completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de62432fb48190b153805b85c4f2d2 completed April 14, 2026, 3:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd55008a5c8190b005a12df7ef2f75 completed May 8, 2026, 3:14 a.m.
Created at: April 10, 2026, 1:08 a.m.