Triple
T12022678
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Iseyin |
E286191
|
entity |
| Predicate | roadConnection |
P385
|
FINISHED |
| Object | Saki |
E286192
|
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: Saki | Statement: [Iseyin, roadConnection, Saki]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Saki Context triple: [Iseyin, roadConnection, Saki]
-
A.
Saki
chosen
Saki is a prominent town in southwestern Nigeria known as a commercial and agricultural hub within Oyo State.
-
B.
Saki
Saki is the pen name of British writer H. H. Munro, best known for his witty, darkly humorous short stories satirizing Edwardian society.
-
C.
Wilkie Cooper
Wilkie Cooper was a British cinematographer known for his work on mid-20th-century films, particularly in the thriller and fantasy genres.
-
D.
Michael Innes
Michael Innes was the pen name of Scottish author J.I.M. Stewart, best known for his erudite and witty detective novels featuring Inspector John Appleby.
-
E.
P. G. Wodehouse
P. G. Wodehouse was an English author celebrated for his witty, farcical comic novels and stories, particularly those featuring Jeeves and Wooster.
- 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_69d6ab4669e48190b59246358b0383ab |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d903ee4f9081909e5a58ecbd830b14 |
completed | April 10, 2026, 2:06 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f48b62cad8819092beb72c604a4762 |
completed | May 1, 2026, 11:15 a.m. |
Created at: April 8, 2026, 9:47 p.m.