Triple
T18339683
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yell |
E439366
|
entity |
| Predicate | hasLargestSettlement |
P235
|
FINISHED |
| Object | Mid Yell |
—
|
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: Mid Yell | Statement: [Yell, hasLargestSettlement, Mid Yell]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mid Yell Context triple: [Yell, hasLargestSettlement, Mid Yell]
-
A.
Mid Yell
chosen
Mid Yell is the main village and administrative hub on the island of Yell in the Shetland Islands, Scotland.
-
B.
Rio Bravo
"Rio Bravo" is a classic 1959 American Western film directed by Howard Hawks, starring John Wayne, Dean Martin, and Ricky Nelson as a young gunslinger.
-
C.
Rainy Mountain
Rainy Mountain is a prominent landmark in Kiowa oral history and culture, serving as a symbolic focal point for ancestral memory and identity.
-
D.
Indian Hills
Indian Hills is a prominent residential neighborhood in Edina, Minnesota, known for its wooded landscapes, curving streets, and upscale homes.
-
E.
Smoky Hills
Smoky Hills is a hilly, grassland-dominated region of north-central Kansas known for its rolling terrain, sandstone and limestone outcrops, and mixed agricultural and prairie landscapes.
- 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_69d8b9175fec8190af865699b4e64d8c |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e50ed07db48190a15e957c96b1c5bf |
completed | April 19, 2026, 5:20 p.m. |
Created at: April 10, 2026, 10:37 a.m.