Triple
T11204098
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Funchal Airport |
E265114
|
entity |
| Predicate | ICAOcode |
P419
|
FINISHED |
| Object | LPMA |
E309608
|
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: LPMA | Statement: [Funchal Airport, ICAOcode, LPMA]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: LPMA Context triple: [Funchal Airport, ICAOcode, LPMA]
-
A.
LPMA
chosen
LPMA is the ICAO airport code for Cristiano Ronaldo Madeira International Airport, the main commercial airport serving the Portuguese island of Madeira.
-
B.
LPAC
LPAC is a regional performing arts venue in Lancaster, California, hosting a wide range of live theater, music, dance, and community events.
-
C.
LMA
LMA is the League Managers Association, the professional body representing and supporting football managers in English leagues.
-
D.
LMA
LMA is a comprehensive system for observing, describing, and interpreting human movement developed from the work of choreographer and movement theorist Rudolf Laban.
-
E.
FLPMA
FLPMA is a 1976 U.S. federal law that governs the management and conservation of public lands administered by the Bureau of Land Management.
- 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_69d6aa9eb9248190b20211772621b4bc |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e8d355c481908fc3d555b596314d |
completed | April 9, 2026, 5:58 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e4972bfbd481908cd0da59389ae17c |
completed | April 19, 2026, 8:49 a.m. |
Created at: April 8, 2026, 9:30 p.m.