Triple

T14727620
Position Surface form Disambiguated ID Type / Status
Subject 12 Play E345984 entity
Predicate hasPart P35 FINISHED
Object Sadie E101492 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: Sadie | Statement: [12 Play, hasPart, Sadie]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sadie
Context triple: [12 Play, hasPart, Sadie]
  • A. Sadie chosen
    "Sadie" is a song by Joanna Newsom from her debut album *The Milk-Eyed Mender*, noted for its intricate harp accompaniment and poetic, emotionally rich lyrics.
  • B. Sadie
    Sadie is a feminine given name commonly used as a diminutive form of Sara or Sarah.
  • C. Sadie Burke
    Sadie Burke is a sharp-tongued, politically savvy aide and confidante to populist governor Willie Stark in the film "All the King's Men."
  • D. Sadie Marks
    Sadie Marks, better known by her stage name Mary Livingstone, was an American radio comedian and actress famed for her long-running role alongside her husband Jack Benny on The Jack Benny Program.
  • E. Sadie Emison Pack
    Sadie Emison Pack was a local woman after whom the town of Sadieville, Kentucky, was named, reflecting her significance in the community’s early history.
  • 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_69d822e5911c8190ba589f957dbd9ba7 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69dec26013c8819090512f8b4df9cc87 completed April 14, 2026, 10:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69fdf099eaf48190b89032b6ac769e67 completed May 8, 2026, 2:18 p.m.
Created at: April 10, 2026, 1:29 a.m.