Triple
T7686621
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | KDTW |
E174133
|
entity |
| Predicate | hasIATACode |
P2569
|
FINISHED |
| Object | DTW |
E172408
|
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: DTW | Statement: [KDTW, hasIATACode, DTW]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: DTW Context triple: [KDTW, hasIATACode, DTW]
-
A.
DTW
chosen
DTW is the IATA airport code for Detroit Metropolitan Wayne County Airport, a major international hub serving the Detroit, Michigan metropolitan area.
-
B.
DTL
DTL is a type of linear accelerator structure that uses a series of drift tubes within an RF cavity to efficiently accelerate charged particle beams.
-
C.
DT
DT is the widely used nickname for Diana Taurasi, a legendary American professional basketball player regarded as one of the greatest in WNBA history.
-
D.
DTS
DTS is a multichannel digital surround sound audio format widely used in home theater systems, cinema, and high-definition media.
-
E.
DTS
DTS is the U.S. Department of Defense’s integrated global transportation network that moves military personnel, equipment, and supplies worldwide.
- 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_69c6995840408190a19de6c51090f46f |
completed | March 27, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69c7022352088190b2510d5fac55864f |
completed | March 27, 2026, 10:18 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c8a25c2a308190908ffdd2f0b7262f |
completed | March 29, 2026, 3:54 a.m. |
Created at: March 27, 2026, 4:02 p.m.