Triple
T14973876
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lynne Frederick |
E373393
|
entity |
| Predicate | startTimeOfSpouseRelationshipWith Peter Sellers |
P67588
|
FINISHED |
| Object | 1977 |
—
|
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: 1977 | Statement: [Lynne Frederick, startTimeOfSpouseRelationshipWith Peter Sellers, 1977]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: startTimeOfSpouseRelationshipWith Peter Sellers Context triple: [Lynne Frederick, startTimeOfSpouseRelationshipWith Peter Sellers, 1977]
-
A.
endTimeOfSpouseRelationshipWithPeterSellers
Indicates the time at which a spouse’s marital relationship with Peter Sellers came to an end.
-
B.
spouseOfSince
chosen
Indicates that two individuals are spouses and specifies the date or time from which their marital relationship has been in effect.
-
C.
endTimeOfSpouse_J. Howard Marshall
Indicates the time at which the marital relationship with J. Howard Marshall ended.
-
D.
startTimeOfSpouseRelationshipWith John Jacob Astor IV
Indicates the point in time when John Jacob Astor IV’s spousal relationship with a partner began.
-
E.
metSpouseElizabethTaylorAt
Indicates that the subject first met their spouse, Elizabeth Taylor, at the specified location or event.
- 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_69d85ccbbcd48190acb56e7cf104d8ad |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded6e767608190940eb6f16ea97451 |
completed | April 15, 2026, 12:08 a.m. |
| PD | Predicate disambiguation | batch_69de9a5d995881909e33658f5aea5582 |
completed | April 14, 2026, 7:49 p.m. |
Created at: April 10, 2026, 2:50 a.m.