Triple
T12078874
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | McAllen International Airport |
E287625
|
entity |
| Predicate | FAA LID |
P420
|
FINISHED |
| Object | MFE |
E963291
|
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: MFE | Statement: [McAllen International Airport, FAA LID, MFE]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: MFE Context triple: [McAllen International Airport, FAA LID, MFE]
-
A.
MFE
chosen
MFE is the three-letter IATA airport code for McAllen International Airport in McAllen, Texas.
-
B.
FRM
FRM is the National Rail station code for Fareham railway station in Hampshire, England.
-
C.
Master of Financial Engineering
The Master of Financial Engineering is a specialized graduate degree program that trains students to apply advanced quantitative, mathematical, and computational methods to finance and risk management.
-
D.
CQF
CQF is the IATA airport code for Calais–Dunkerque Airport in northern France.
-
E.
CQF
CQF (Cyclic Queuing and Forwarding) is a time-sensitive networking mechanism defined in IEEE 802.1Qch that provides deterministic, low-latency packet forwarding using cyclic transmission queues.
- 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_69d6ab4846e081908ee7bbd66a6d3459 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d9045e81f88190be2b1aabd93f077c |
completed | April 10, 2026, 2:08 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f60a6b2d788190975275d713c26a4e |
completed | May 2, 2026, 2:30 p.m. |
Created at: April 8, 2026, 9:48 p.m.