Triple
T9727911
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | One Hundred Days |
E235661
|
entity |
| Predicate | aboutPerson |
P2308
|
FINISHED |
| Object | Sandy Woodward |
E854676
|
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: Sandy Woodward | Statement: [One Hundred Days, aboutPerson, Sandy Woodward]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sandy Woodward Context triple: [One Hundred Days, aboutPerson, Sandy Woodward]
-
A.
Sandy Woodward
chosen
Sandy Woodward was a British Royal Navy admiral best known for commanding the UK task force during the 1982 Falklands War.
-
B.
Sandy Richardson
Sandy Richardson is a central character in the long-running British television soap opera "Crossroads."
-
C.
Elaine Winstone
Elaine Winstone is the wife of English actor Ray Winstone and the mother of actress Jaime Winstone.
-
D.
Susan Woodward
Susan Woodward is a noted American economist and author recognized for her work on financial markets, consumer finance, and economic policy.
-
E.
Sybil Williams
Sybil Williams was a Welsh actress and theater producer best known as the first wife of actor Richard Burton and later as a prominent New York nightclub owner.
- 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_69ca84d0fad481909cdd45aa77416c48 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cd9e7af544819090a8a1adec41943c |
completed | April 1, 2026, 10:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d74fb63b7081909cb6faddd795ced6 |
completed | April 9, 2026, 7:05 a.m. |
Created at: March 30, 2026, 8:21 p.m.