Triple
T20614389
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Indianapolis Ice |
E506527
|
entity |
| Predicate | city |
P40
|
FINISHED |
| Object | Indianapolis |
—
|
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: Indianapolis | Statement: [Indianapolis Ice, city, Indianapolis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Indianapolis Context triple: [Indianapolis Ice, city, Indianapolis]
-
A.
Indianapolis
chosen
Indianapolis is the capital and most populous city of the U.S. state of Indiana, known for its major sports franchises and hosting the annual Indianapolis 500 auto race.
-
B.
South Bend
South Bend is a small coastal city in southwestern Washington State that serves as the county seat of Pacific County.
-
C.
Indy
Indy is a compact UNIX workstation developed by Silicon Graphics in the early 1990s, notable for its advanced graphics and multimedia capabilities for its time.
-
D.
Indy
Indy is the adventurous archaeologist and whip-wielding hero at the center of the Indiana Jones film franchise.
-
E.
Indy
Indy is a recurring character in the animated children's series "Bluey," known as one of Bluey's imaginative and energetic dog friends.
- 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_69e0b4bc90988190ac360aaf645efc1d |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6aada19e481909363428ceda67603 |
completed | April 20, 2026, 10:38 p.m. |
Created at: April 16, 2026, 11:41 a.m.