Triple
T15716931
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Moshoeshoe I International Airport |
E380984
|
entity |
| Predicate | hasCode |
P9567
|
FINISHED |
| Object | FXMM |
E1172750
|
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: FXMM | Statement: [Moshoeshoe I International Airport, hasCode, FXMM]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: FXMM Context triple: [Moshoeshoe I International Airport, hasCode, FXMM]
-
A.
FXMM
chosen
FXMM is the ICAO airport code assigned to Moshoeshoe I International Airport in Lesotho.
-
B.
FXM
FXM is an American cable television channel owned by FX Networks that primarily airs movies, including contemporary films and classic titles.
-
C.
FX
FX is the identifying squadron code historically used by No. 92 Squadron of the Royal Air Force.
-
D.
FX
FX is an American cable television network known for airing edgy, critically acclaimed original series and dramas.
-
E.
FX2
FX2 is a 1991 action-thriller film and sequel to the movie "F/X," starring Brian Dennehy and Bryan Brown as they again use movie special-effects skills to outwit criminals.
- 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_69d86d9bf930819082b30cf6d169297c |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e04f91beb08190bd91bf9306737c3b |
completed | April 16, 2026, 2:55 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff82f464008190ae0e79f50b9b3eb3 |
completed | May 9, 2026, 6:54 p.m. |
Created at: April 10, 2026, 4:45 a.m.