Triple

T17971980
Position Surface form Disambiguated ID Type / Status
Subject House of Blois E449369 entity
Predicate hasTitle P38 FINISHED
Object Counts of Aumale 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: Counts of Aumale | Statement: [House of Blois, hasTitle, Counts of Aumale]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Counts of Aumale
Context triple: [House of Blois, hasTitle, Counts of Aumale]
  • A. Amaunet
    Amaunet is an ancient Egyptian primordial goddess associated with hiddenness and the air, venerated as one of the eight creator deities of Hermopolis.
  • B. Count of Retamoso
    Count of Retamoso is a Spanish noble title historically associated with Agustín Fernando Muñoz y Sánchez, the morganatic husband of Queen Maria Christina of the Two Sicilies.
  • C. Amausi
    Amausi is a locality in Lucknow, India, best known for hosting the city’s main airport and associated transport and commercial facilities.
  • D. Count of Angera
    Count of Angera is a noble title historically associated with the influential Italian Borromeo family, linked to their feudal holdings around the town of Angera on Lake Maggiore.
  • E. Aumale chosen
    Aumale is a historic town and former county in Normandy, France, notable for its medieval noble associations.
  • 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_69d8b9f9927c8190a006110c8b996e61 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e4b1fb58c481909726d6f916f6f646 completed April 19, 2026, 10:44 a.m.
Created at: April 10, 2026, 10:22 a.m.