Triple
T1158870
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Terminal 2 (José Martí International Airport) |
E24448
|
entity |
| Predicate | hasIATACode |
P2569
|
FINISHED |
| Object | HAV |
E24064
|
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: HAV | Statement: [Terminal 2 (José Martí International Airport), hasIATACode, HAV]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: HAV Context triple: [Terminal 2 (José Martí International Airport), hasIATACode, HAV]
-
A.
HAV
chosen
HAV is the IATA airport code for José Martí International Airport, the main international gateway serving Havana, Cuba.
-
B.
HA
HA is the IATA airline designator for Hawaiian Airlines, the largest and longest-serving commercial airline based in Hawaii.
-
C.
HAA
HAA is the Harvard Alumni Association, the organization that connects and serves Harvard University’s global community of alumni.
-
D.
HB
HB is the second-generation Holden Torana small family car series produced in the late 1960s, known for introducing more modern styling and engineering updates over its predecessor.
-
E.
HN
HN is the two-letter ISO 3166-1 alpha-2 country code assigned to Honduras.
- 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_69a494060e148190abb42f971242c197 |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4bcad47a08190895769611798f67f |
completed | March 1, 2026, 10:24 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ac667d2bdc8190b7d797683a4d3fe8 |
completed | March 7, 2026, 5:55 p.m. |
Created at: March 1, 2026, 7:45 p.m.