Triple

T13730166
Position Surface form Disambiguated ID Type / Status
Subject Raoul d’Harcourt E329774 entity
Predicate nobleFamily P914 FINISHED
Object Harcourt family E554575 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: Harcourt family | Statement: [Raoul d’Harcourt, nobleFamily, Harcourt family]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Harcourt family
Context triple: [Raoul d’Harcourt, nobleFamily, Harcourt family]
  • A. Harcourt family chosen
    The Harcourt family is an old English noble lineage historically associated with the village and estate of Stanton Harcourt in Oxfordshire.
  • B. Hall family
    The Hall family is a familial group or lineage to which Sylvia Hall belongs.
  • C. Henry family
    The Henry family is a lineage whose surname is associated with the historic Henry House and its heritage.
  • D. Howard family
    The Howard family is an American show-business family best known for actors and filmmakers like Rance Howard and his son Ron Howard.
  • E. Howard family
    The Howard family is a prominent English noble house that has long held the dukedom of Norfolk and played a major role in the political and social life of the British aristocracy.
  • 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_69d80772315881908f980cae40d91664 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69de01f92b588190be97ec4564dddd59 completed April 14, 2026, 8:59 a.m.
NED1 Entity disambiguation (via context triple) batch_69f79d65062c819086a5f7a7ebc45412 completed May 3, 2026, 7:09 p.m.
Created at: April 9, 2026, 9:55 p.m.