Triple

T12888823
Position Surface form Disambiguated ID Type / Status
Subject Joan Benedict E308302 entity
Predicate familyName P18 FINISHED
Object Benedict E42638 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: Benedict | Statement: [Joan Benedict, familyName, Benedict]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Benedict
Context triple: [Joan Benedict, familyName, Benedict]
  • A. Benedict chosen
    Benedict is a masculine given name of Latin origin, most famously borne in modern times by the British actor Benedict Cumberbatch.
  • B. Benedict Bogeaus
    Benedict Bogeaus was a mid-20th-century independent film producer known for backing a variety of Hollywood features outside the major studio system.
  • C. Benedetto
    Benedetto is the Italian form of the given name Benedict, traditionally associated with blessings and several notable religious and historical figures.
  • D. Ambrose
    Ambrose is a masculine given name of Latin origin, historically associated with early Christian saints and notable figures such as the American Civil War general Ambrose E. Burnside.
  • E. Ambrose
    Ambrose is the middle name of John Ambrose Fleming, the British electrical engineer and physicist known for inventing the vacuum tube diode.
  • 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_69d7bdf7c1f0819098102569a8d8cbf5 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d9714581988190afc720ffd7797860 completed April 10, 2026, 9:53 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6a5598ad08190bad57ccfb4e4e2b6 completed May 3, 2026, 1:31 a.m.
Created at: April 9, 2026, 5:39 p.m.