Triple
T8188737
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Terminal 4 (Mehrabad International Airport) |
E191251
|
entity |
| Predicate | hasIATACodeAirport |
P2569
|
FINISHED |
| Object | THR |
E189764
|
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: THR | Statement: [Terminal 4 (Mehrabad International Airport), hasIATACodeAirport, THR]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: THR Context triple: [Terminal 4 (Mehrabad International Airport), hasIATACodeAirport, THR]
-
A.
THR
chosen
THR is the IATA airport code for Mehrabad International Airport, a major airport serving Tehran, Iran.
-
B.
TH
TH is the two-letter ISO 3166-1 alpha-2 country code assigned to Thailand for international standardization and identification.
-
C.
TRL
TRL is the FAA location identifier for Terrell Municipal Airport in Terrell, Texas.
-
D.
TRL
TRL is a popular abbreviation for "Total Request Live," a former MTV music video countdown show that became a major pop culture phenomenon in the late 1990s and early 2000s.
-
E.
TW
TW is the two-letter ISO 3166 country code assigned to Taiwan (commonly referred to as Chinese Taipei in certain international contexts).
- 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_69ca82c5b6948190a583c096fb0a6c71 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb4d9f4a488190b39bdc1792646914 |
completed | March 31, 2026, 4:29 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cced8da28c81909c34c0103da68f0f |
completed | April 1, 2026, 10:03 a.m. |
Created at: March 30, 2026, 5:41 p.m.