Triple
T23238436
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jacqueline Cochran Regional Airport |
E581367
|
entity |
| Predicate | IATACode |
P418
|
FINISHED |
| Object | TRM |
—
|
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: TRM | Statement: [Jacqueline Cochran Regional Airport, IATACode, TRM]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: TRM Context triple: [Jacqueline Cochran Regional Airport, IATACode, TRM]
-
A.
TRM
chosen
TRM is the IATA airport code for Jacqueline Cochran Regional Airport serving the Thermal, California area.
-
B.
TRN
TRN is the IATA airport code for Turin Airport, the main international airport serving Turin in northern Italy.
-
C.
KTRM
KTRM is the ICAO code for Jacqueline Cochran Regional Airport, a public airport serving the Thermal, California area.
-
D.
TRF
TRF is the IATA airport code for Sandefjord Airport, Torp, a regional international airport serving the Sandefjord and Oslo area in Norway.
-
E.
TRC
TRC is the national railway operator of Tanzania, responsible for managing and running the country’s rail transport services.
- 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_69e2460556f88190be1744a84a84173f |
completed | April 17, 2026, 2:39 p.m. |
| NER | Named-entity recognition | batch_69f192ebaef4819083a7805537ad993f |
completed | April 29, 2026, 5:11 a.m. |
Created at: April 17, 2026, 4:10 p.m.