Triple
T9970529
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Alma Beers Del Mar |
E196190
|
entity |
| Predicate | spouseOf |
P13
|
FINISHED |
| Object | Ennis Del Mar |
E303088
|
NE 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: Ennis Del Mar | Statement: [Alma Beers Del Mar, spouseOf, Ennis Del Mar]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ennis Del Mar Context triple: [Alma Beers Del Mar, spouseOf, Ennis Del Mar]
-
A.
Ennis Del Mar
chosen
Ennis Del Mar is a reserved Wyoming ranch hand whose complex, decades-long romantic relationship with Jack Twist forms the emotional core of the film and short story "Brokeback Mountain."
-
B.
Ennis
Ennis is a town in County Clare, Ireland, historically notable as a parliamentary constituency represented in the UK Parliament.
-
C.
Ennis
Ennis is a small Texas city known for its historic downtown, annual Bluebonnet Trails Festival, and location along major transportation routes south of Dallas.
-
D.
Lundey
Lundey is a small, uninhabited island off the coast of Reykjavík, Iceland, best known as a nesting site for Atlantic puffins and other seabirds.
-
E.
Doheny
Doheny is a surname most notably associated with Edward L. Doheny, an American oil tycoon and early petroleum industry pioneer.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca82eea2b88190a0e511d21a31f386 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdb7b7ea9881908a56f11e2e446dd0 |
completed | April 2, 2026, 12:26 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d23dca14d081909573e91a576921c9 |
completed | April 5, 2026, 10:47 a.m. |
Created at: March 30, 2026, 8:48 p.m.