Triple
T7875059
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Athina Onassis (Tina Livanos) |
E182829
|
entity |
| Predicate | endTime (marriage to Aristotle Onassis) |
P79510
|
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: [Athina Onassis (Tina Livanos), endTime (marriage to Aristotle Onassis), 1960]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: endTime (marriage to Aristotle Onassis) Context triple: [Athina Onassis (Tina Livanos), endTime (marriage to Aristotle Onassis), 1960]
-
A.
endTime (marriage to Joséphine)
Indicates the point in time at which the marriage to Joséphine legally or formally ended.
-
B.
endTime (marriage to Liza Minnelli)
Indicates the date and time when the marriage to Liza Minnelli legally or formally ended.
-
C.
endTime (marriage to Nero)
Indicates the point in time at which the marriage to Nero concluded or was terminated.
-
D.
endTime (marriage to Donald Trump)
Indicates the date and time at which the marriage to Donald Trump legally or formally concluded.
-
E.
endTime (spouse: Wallis Simpson)
Indicates the point in time at which the marital relationship with Wallis Simpson concluded.
- F. None of above. chosen
Provenance (4 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_69ca828a17248190b46defe758bc5ad3 |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb39a961188190b2f12f8fe5d66641 |
completed | March 31, 2026, 3:04 a.m. |
| PD | Predicate disambiguation | batch_69cae928e1b88190b0620f4c4f03bc7d |
completed | March 30, 2026, 9:20 p.m. |
| PDg | Predicate description generation | batch_69caf786ec748190b6347b0c94335550 |
completed | March 30, 2026, 10:21 p.m. |
Created at: March 30, 2026, 4:56 p.m.