Triple
T18869005
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Micheline Presle |
E461517
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | William Marshall |
—
|
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: William Marshall | Statement: [Micheline Presle, spouse, William Marshall]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: William Marshall Context triple: [Micheline Presle, spouse, William Marshall]
-
A.
William Marshall
William Marshall is an individual best known under the name Bill Marshall, likely recognized in public or professional contexts by that primary name.
-
B.
William Marshall
William Marshall was an American actor, director, and occasional singer active in mid-20th-century film and theater.
-
C.
William Marshall
William Marshall was an early 20th-century American cinematographer known for his work on silent-era films.
-
D.
William Marshall
chosen
William Marshall was an American big band leader, vocalist, and actor active in the mid-20th century.
-
E.
Sir William Marshall
Sir William Marshall was a British Army general best known for leading successful campaigns in the Mesopotamian theatre during World War I.
- 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_69d8dcfb7b9c8190854e7b171b98ea2e |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5c2a7e1308190a1667d2d2d43df6c |
completed | April 20, 2026, 6:07 a.m. |
Created at: April 10, 2026, 11:57 a.m.