Triple

T5208721
Position Surface form Disambiguated ID Type / Status
Subject Royal Mausoleum, Frogmore E117574 entity
Predicate architect P184 FINISHED
Object A. J. Humbert E85637 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: A. J. Humbert | Statement: [Royal Mausoleum, Frogmore, architect, A. J. Humbert]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: A. J. Humbert
Context triple: [Royal Mausoleum, Frogmore, architect, A. J. Humbert]
  • A. A. J. Humbert chosen
    A. J. Humbert was a 19th-century British architect known for his work on royal residences, including commissions for the British royal family.
  • B. Samuel Dracutt
    Samuel Dracutt was a historical figure after whom the town of Dracut, Massachusetts, was named, likely an early landowner or prominent local settler.
  • C. George Faber
    George Faber is a British television and film producer known for his work on acclaimed dramas and biographical films.
  • D. Brian Faulkner
    Brian Faulkner was a prominent Northern Irish politician who served as the last Prime Minister of Northern Ireland before the government’s suspension in 1972.
  • E. Louis Bayard
    Louis Bayard is an American novelist known for his historical mysteries and literary thrillers, including the novel that inspired "The Pale Blue Eye."
  • 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_69bd4463dd3c81909966123f20b79d57 completed March 20, 2026, 12:58 p.m.
NER Named-entity recognition batch_69bd7a6f0ffc819090b8b59fc22f4dae completed March 20, 2026, 4:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69beefd4b75c8190b1b87b8d93925245 completed March 21, 2026, 7:21 p.m.
Created at: March 20, 2026, 1:47 p.m.