Triple
T33294564
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tova Traesnaes |
E852403
|
entity |
| Predicate | marriageEndWithErnestBorgnine |
P193073
|
FINISHED |
| Object | 2012 |
—
|
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: 2012 | Statement: [Tova Traesnaes, marriageEndWithErnestBorgnine, 2012]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: marriageEndWithErnestBorgnine Context triple: [Tova Traesnaes, marriageEndWithErnestBorgnine, 2012]
-
A.
marriageStartWithErnestBorgnine
Indicates the point in time when a marriage involving Ernest Borgnine began.
-
B.
marriageEndWithRobReiner
Indicates that a marriage concluded or was terminated in connection with Rob Reiner (i.e., that Rob Reiner was one of the spouses and the marriage ended).
-
C.
marriageEndWithBillyZane
Indicates that a marriage concludes or is terminated in connection with Billy Zane.
-
D.
marriageEndWith Mark-Paul Gosselaar
Indicates that a marriage involving Mark-Paul Gosselaar has come to an end (e.g., through divorce or annulment).
-
E.
marriageEndToGlennFord
Indicates the termination or end of a marriage in which Glenn Ford is one of the spouses.
- 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_69f349660ff48190a4568803d0b89941 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69fd37b695c88190855801626f91c4cd |
completed | May 8, 2026, 1:09 a.m. |
| PD | Predicate disambiguation | batch_69fd374cccf08190a230e87164af5938 |
completed | May 8, 2026, 1:07 a.m. |
| PDg | Predicate description generation | batch_69fd37b45b4481908b947b52fbcb7ade |
completed | May 8, 2026, 1:09 a.m. |
Created at: May 1, 2026, 1:33 a.m.