Triple
T26603784
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Myrtle Reeves |
E667711
|
entity |
| Predicate | marriageEndToOliverHardy |
P169237
|
FINISHED |
| Object | 1921 |
—
|
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: 1921 | Statement: [Myrtle Reeves, marriageEndToOliverHardy, 1921]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: marriageEndToOliverHardy Context triple: [Myrtle Reeves, marriageEndToOliverHardy, 1921]
-
A.
marriageStartToOliverHardy
Indicates the time or event at which a subject entered into marriage with Oliver Hardy.
-
B.
marriageEndToLorettaYoung
Indicates that a marriage ended with the person Loretta Young as one of the spouses.
-
C.
marriageEndToGlennFord
Indicates the termination or end of a marriage in which Glenn Ford is one of the spouses.
-
D.
marriageEndWithJohnBarrymore
Indicates that a marriage concluded (e.g., by divorce or separation) in which one of the spouses was John Barrymore.
-
E.
marriageToCharlieChaplinEnd
Indicates the point or event at which a marriage to Charlie Chaplin comes to an end (e.g., through divorce, annulment, or death).
- 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_69ee9cfd20348190bb1255d2603efb7a |
completed | April 26, 2026, 11:17 p.m. |
| NER | Named-entity recognition | batch_69f67d691a948190afa7fb19ae7d4ac5 |
completed | May 2, 2026, 10:40 p.m. |
| PD | Predicate disambiguation | batch_69f678cc272081909e5c70f1bc7407f0 |
completed | May 2, 2026, 10:21 p.m. |
| PDg | Predicate description generation | batch_69f67c9ec1708190b26ccf402ed7b106 |
completed | May 2, 2026, 10:37 p.m. |
Created at: April 27, 2026, 2:13 a.m.