Triple
T1086611
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rancho-Boyeros Airport |
E24065
|
entity |
| Predicate | ICAOcode |
P419
|
FINISHED |
| Object | MUHA |
E125038
|
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: MUHA | Statement: [Rancho-Boyeros Airport, ICAOcode, MUHA]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: MUHA Context triple: [Rancho-Boyeros Airport, ICAOcode, MUHA]
-
A.
MUHA
chosen
MUHA is the ICAO airport code for José Martí International Airport, the main international gateway serving Havana, Cuba.
-
B.
Muh-he-con-neok
Muh-he-con-neok is an alternative historical name for the Mahican, a Native American people originally from the Hudson River Valley region.
-
C.
Munnik
Munnik is a given name associated with J. B. M. Hertzog, a prominent early 20th-century South African prime minister and political leader.
-
D.
MH
MH is the official vehicle registration code assigned to the Indian state of Maharashtra.
-
E.
MH
MH is the two-letter IATA airline designator used to identify Malaysia Airlines on tickets, timetables, and flight numbers.
- 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_69a49404428c819092dcc9632f5f7b8b |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4b963161081908a523c8d63871652 |
completed | March 1, 2026, 10:10 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ac4c243cbc81908d6101faad628fc8 |
completed | March 7, 2026, 4:02 p.m. |
Created at: March 1, 2026, 7:42 p.m.