Triple

T20400621
Position Surface form Disambiguated ID Type / Status
Subject Standing Fast E500320 entity
Predicate coAuthor P398 FINISHED
Object Tom Mathews NE NERFINISHED

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: Tom Mathews | Statement: [Standing Fast, coAuthor, Tom Mathews]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tom Mathews
Context triple: [Standing Fast, coAuthor, Tom Mathews]
  • A. Tom Mathews chosen
    Tom Mathews is an American writer and journalist known for co-authoring civil rights leader Roy Wilkins’s autobiography, "Standing Fast."
  • B. William Mathews
    William Mathews was a 19th-century British mountaineer notable for pioneering ascents in the Alps.
  • C. Richard Mathews
    Richard Mathews is an actor known for playing the Time Lord Rassilon in the long-running British science fiction series Doctor Who.
  • D. John Matthews
    John Matthews is a relatively common personal name shared by numerous individuals across various professions and public roles.
  • E. Peter Mathews
    Peter Mathews is a prominent scholar of Maya hieroglyphic writing, known for his influential contributions to the decipherment and understanding of Maya epigraphy.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0b4a81bec8190b69adfdc1336a015 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6798db79c819085e3a2526538726f completed April 20, 2026, 7:07 p.m.
Created at: April 16, 2026, 11:29 a.m.