Triple
T1893155
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | BAL |
E41917
|
entity |
| Predicate | hasIATAStyleFormat |
P2569
|
FINISHED |
| Object | three-letter code similar to airport codes |
—
|
LITERAL 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: three-letter code similar to airport codes | Statement: [BAL, hasIATAStyleFormat, three-letter code similar to airport codes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasIATAStyleFormat Context triple: [BAL, hasIATAStyleFormat, three-letter code similar to airport codes]
-
A.
hasIATAcode
chosen
Indicates that an entity, typically a transportation facility like an airport, is associated with a specific IATA (International Air Transport Association) code.
-
B.
hasAirportCodeType
Indicates that an airport code is associated with a specific classification or type (e.g., IATA, ICAO, FAA).
-
C.
travelDocumentNumberFormat
Indicates the specific structural pattern or rules that define how a travel document number must be formatted.
-
D.
hasFourLetterCode
Indicates that an entity is associated with a code consisting of exactly four characters.
-
E.
isTwoLetterCode
Indicates that something functions as a two-letter abbreviated code representing a larger name or concept.
- F. None of above.
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_69a8864b6de0819098d089f6a1b910a7 |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69abb1480a6c81909fcf5cce4c42fed4 |
completed | March 7, 2026, 5:02 a.m. |
| PD | Predicate disambiguation | batch_69abafe7e7e88190b58c0df59187c0c2 |
completed | March 7, 2026, 4:56 a.m. |
Created at: March 4, 2026, 7:34 p.m.