Triple
T14065937
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Susannah York |
E338470
|
entity |
| Predicate | startTime (spouse: Michael Wells) |
P14428
|
FINISHED |
| Object | 1960 |
—
|
LITERAL 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: 1960 | Statement: [Susannah York, startTime (spouse: Michael Wells), 1960]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: startTime (spouse: Michael Wells) Context triple: [Susannah York, startTime (spouse: Michael Wells), 1960]
-
A.
spouseStartTime
chosen
Indicates the point in time when two individuals began their spousal (marriage) relationship.
-
B.
startTime (spouse: Mike Tyson)
Indicates the specific time at which the event or relationship involving the spouse Mike Tyson begins.
-
C.
startTime (marriage to Liza Minnelli)
Indicates the date and time when the marriage to Liza Minnelli began.
-
D.
startTime (marriage to Paul Mowrer)
Indicates the date and time when the marriage to Paul Mowrer began.
-
E.
startTime (spouse: Wallis Simpson)
Indicates the specific point in time when the spousal relationship with Wallis Simpson began.
- F. None of above.
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_69d81c67ba6c819091935650dfb3b895 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de568b81f08190a571004261c0e8e4 |
completed | April 14, 2026, 3 p.m. |
| PD | Predicate disambiguation | batch_69de05adef888190b023ab42ef5076b6 |
completed | April 14, 2026, 9:15 a.m. |
Created at: April 9, 2026, 10:21 p.m.