Triple
T35348784
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jenny Sanford |
E1020816
|
entity |
| Predicate | endTime (marriage to Mark Sanford) |
P92796
|
FINISHED |
| Object | 2010 |
—
|
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: 2010 | Statement: [Jenny Sanford, endTime (marriage to Mark Sanford), 2010]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: endTime (marriage to Mark Sanford) Context triple: [Jenny Sanford, endTime (marriage to Mark Sanford), 2010]
-
A.
endTime (marriage to Donald Trump)
Indicates the date and time at which the marriage to Donald Trump legally or formally concluded.
-
B.
endTime (marriage to Jaime de Marichalar)
Indicates the time at which the marriage to Jaime de Marichalar officially ended.
-
C.
endTime (marriage)
chosen
Indicates the point in time at which the marriage relationship is considered to have ended.
-
D.
endTime (marriage to Autumn Kelly)
Indicates the time at which the marriage to Autumn Kelly concluded or was formally ended.
-
E.
endTime (marriage to Brigitte Bardot)
Indicates the date and time at which the marriage to Brigitte Bardot legally or formally ended.
- 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_69f76decd95c8190ae428f6a19d535de |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69fec00f27988190955de6b6348a4d97 |
completed | May 9, 2026, 5:03 a.m. |
| PD | Predicate disambiguation | batch_69febd52037c8190b475dbd50fdbc13e |
completed | May 9, 2026, 4:51 a.m. |
Created at: May 3, 2026, 4:03 p.m.