Triple

T22045100
Position Surface form Disambiguated ID Type / Status
Subject Charles Boberg E544739 entity
Predicate coAuthorWith P398 FINISHED
Object Sharon Ash 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: Sharon Ash | Statement: [Charles Boberg, coAuthorWith, Sharon Ash]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sharon Ash
Context triple: [Charles Boberg, coAuthorWith, Sharon Ash]
  • A. Sharon Ash chosen
    Sharon Ash is a linguist known for her research on regional variation in American English, particularly within the Inland North dialect region.
  • B. Sharon Arden
    Sharon Arden is the maiden name of Sharon Osbourne, the British television personality, music manager, and wife of rock singer Ozzy Osbourne.
  • C. Sharon Farrell
    Sharon Farrell is an American actress known for her work in film and television from the 1960s onward, often appearing in teen comedies, dramas, and genre movies.
  • D. Sharon Pintey
    Sharon Pintey is a fictional character from the British film "Cashback," portrayed by actress Emilia Fox.
  • E. Sharon Paisley
    Sharon Paisley is a member of the prominent Paisley family from Northern Ireland, related to political figure Rhonda Paisley.
  • 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_69e11e32445c8190ab97089b48a130bb completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f1282e647481908e054b3ad19e2c15 completed April 28, 2026, 9:35 p.m.
Created at: April 16, 2026, 8:25 p.m.