Triple
T26603793
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Myrtle Reeves |
E667711
|
entity |
| Predicate | relationshipToOliverHardy |
P197545
|
FINISHED |
| Object | first spouse |
—
|
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: first spouse | Statement: [Myrtle Reeves, relationshipToOliverHardy, first spouse]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipToOliverHardy Context triple: [Myrtle Reeves, relationshipToOliverHardy, first spouse]
-
A.
marriageStartToOliverHardy
Indicates the time or event at which a subject entered into marriage with Oliver Hardy.
-
B.
marriageEndToOliverHardy
Indicates that a marriage ended in relation to Oliver Hardy, specifying the termination of a marital relationship involving him.
-
C.
partnerInComedyDuo
Indicates that two entities are partners together in a comedy duo act or performance team.
-
D.
roleOfGracieAllen
Indicates that the specified role or function is performed or held by Gracie Allen.
-
E.
relationshipTypeWithDirkDiggler
Indicates the specific nature or category of relationship that an entity has with Dirk Diggler.
- 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_69fe9b0276d48190b554fa22b043e6d8 |
completed | May 9, 2026, 2:25 a.m. |
| PD | Predicate disambiguation | batch_69fe999692b081909921e1148d66f0ef |
completed | May 9, 2026, 2:19 a.m. |
| PDg | Predicate description generation | batch_69fe9b013ec481908f89beddb9c4cd4e |
completed | May 9, 2026, 2:25 a.m. |
Created at: April 27, 2026, 2:13 a.m.