Triple
T4228082
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tepehuan |
E94508
|
entity |
| Predicate | neighboringGroup |
P5965
|
FINISHED |
| Object | Cora |
E79964
|
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: Cora | Statement: [Tepehuan, neighboringGroup, Cora]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cora Context triple: [Tepehuan, neighboringGroup, Cora]
-
A.
Cora
chosen
Cora is an indigenous Uto-Aztecan language spoken primarily by the Cora people in the Sierra del Nayar region of western Mexico.
-
B.
Cora
Cora is the surname of Alex Cora, a former Major League Baseball infielder and current manager known for leading the Boston Red Sox.
-
C.
Cora Hudson
Cora Hudson is a supporting character on the sitcom "Mork & Mindy," known as Mindy’s warm, down-to-earth grandmother.
-
D.
Cora Smith
Cora Smith is the seductive and scheming femme fatale who conspires with her lover to murder her husband in the classic film noir The Postman Always Rings Twice (1946).
-
E.
Cora Crane
Cora Crane was an American writer, journalist, and proprietor of a Jacksonville, Florida brothel, best known for her long-term relationship with author Stephen Crane and her vivid reportage from the Spanish-American War.
- 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_69b3453700a08190ae88792e3dc63207 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b34e51817c8190bff50f2c3b5deea0 |
completed | March 12, 2026, 11:37 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5964a388881908038e5a612424b9b |
completed | March 14, 2026, 5:09 p.m. |
Created at: March 12, 2026, 11:04 p.m.