Triple
T12296607
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sheila Williams |
E293102
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Sheila Williams |
E293102
|
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: Sheila Williams | Statement: [Sheila Williams, name, Sheila Williams]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sheila Williams Context triple: [Sheila Williams, name, Sheila Williams]
-
A.
Sheila Williams
chosen
Sheila Williams is an acclaimed science fiction editor best known for her long tenure as editor of Asimov’s Science Fiction magazine.
-
B.
Yvette Williams
Yvette Williams was a pioneering New Zealand long jumper and Olympic gold medallist who became one of the country’s most celebrated track and field athletes of the 1950s.
-
C.
Sharon Williams
Sharon Williams is known for being the first wife of acclaimed film director James Cameron.
-
D.
Yolanda Williams
Yolanda Williams is best known as the wife of legendary American boxer Muhammad Ali.
-
E.
Jennifer Sorrell
Jennifer Sorrell is best known as the wife of acclaimed Indian-British actor Saeed Jaffrey.
- 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_69d6ab690ad081908c0ed3870ec82d53 |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d93ed903808190b7ed90e0db3d7586 |
completed | April 10, 2026, 6:18 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6718199d0819088eff94c031d2fe1 |
completed | May 2, 2026, 9:49 p.m. |
Created at: April 8, 2026, 9:52 p.m.