Triple
T21188974
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael Dorman |
E522161
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Triangle |
—
|
NE NERFINISHED |
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: Triangle | Statement: [Michael Dorman, notableWork, Triangle]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Triangle Context triple: [Michael Dorman, notableWork, Triangle]
-
A.
Triangle
Triangle is a small sugar-producing town in southeastern Zimbabwe known for its large sugar estates and milling operations.
-
B.
Triangle
chosen
"Triangle" is a 2009 psychological horror-thriller film known for its mind-bending time-loop narrative and unsettling atmosphere.
-
C.
Triangle
Triangle is a British television drama series, best known for its stories set aboard a North Sea ferry and for featuring actress Kate O'Mara.
-
D.
Triangles
"Triangles" is a notable photographic work by American photographer Imogen Cunningham, exemplifying her modernist approach and emphasis on abstract geometric forms.
-
E.
Trianguli
Trianguli is the Latin genitive form of Triangulum, the name of a small constellation in the northern sky.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b51061388190aa03f19700d3ef04 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e733350e588190a31467758a8afa5c |
completed | April 21, 2026, 8:20 a.m. |
Created at: April 16, 2026, 3:07 p.m.