Triple
T17465382
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Illini |
E425262
|
entity |
| Predicate | relatedService |
P12758
|
FINISHED |
| Object | Saluki |
—
|
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: Saluki | Statement: [Illini, relatedService, Saluki]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Saluki Context triple: [Illini, relatedService, Saluki]
-
A.
Saluki
chosen
The Saluki is an Amtrak passenger train service operating in the Midwest, primarily connecting Chicago with Carbondale, Illinois.
-
B.
Talbot hound
The Talbot hound is a now-extinct, large white hunting dog of medieval England, famed for its tracking ability and frequently used as a heraldic emblem.
-
C.
Greyhound
Greyhound is a 2020 World War II naval thriller film starring Tom Hanks as a U.S. destroyer captain escorting Allied convoys across the Atlantic while evading German U-boats.
-
D.
Greyhound
Greyhound is a breed of tall, slender sighthound renowned for its exceptional speed and grace, historically used for hunting and racing.
-
E.
Greyhound
Greyhound is a long-distance intercity bus service brand known for its extensive coach network across North America.
- 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_69d889dbc2e88190b18ea6115e819258 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e451a6c2e08190bca9de56ee2f5136 |
completed | April 19, 2026, 3:53 a.m. |
Created at: April 10, 2026, 5:47 a.m.