Triple
T10936976
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hilary Swank |
E258358
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Swank |
E258358
|
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: Swank | Statement: [Hilary Swank, familyName, Swank]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Swank Context triple: [Hilary Swank, familyName, Swank]
-
A.
Renée Zellweger
Renée Zellweger is an Academy Award–winning American actress best known for her versatile performances in films such as Jerry Maguire, Chicago, and the Bridget Jones series.
-
B.
Constanta Hopkins
Constanta Hopkins was a member of the early 17th-century Hopkins family associated with the Mayflower Pilgrims and the Plymouth Colony.
-
C.
Witherspoon
Witherspoon is a Scottish-origin surname borne by various notable figures in politics, entertainment, and sports.
-
D.
Jolie
Jolie is a nickname for Al Jolson, the influential early 20th-century American singer and entertainer often called "the world's greatest entertainer."
-
E.
Hilary Swank
chosen
Hilary Swank is an American actress and two-time Academy Award winner known for her intense, transformative performances in films such as "Boys Don't Cry" and "Million Dollar Baby."
- 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_69d6aa8769b4819082bfe5e61b9017f0 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d770b065288190b4216beee8e8a193 |
completed | April 9, 2026, 9:26 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e23bfd6a108190a0557598f68659fa |
completed | April 17, 2026, 1:56 p.m. |
Created at: April 8, 2026, 9:23 p.m.