Triple
T10640701
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Logan Terminal A |
E250711
|
entity |
| Predicate | hasIATACode |
P2569
|
FINISHED |
| Object | BOS |
E48656
|
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: BOS | Statement: [Logan Terminal A, hasIATACode, BOS]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: BOS Context triple: [Logan Terminal A, hasIATACode, BOS]
-
A.
BOS
chosen
BOS is the three-letter IATA airport code for Boston Logan International Airport, the primary airport serving the Boston, Massachusetts area.
-
B.
BOS
BOS is the standard three-letter abbreviation used to represent the Boston Braves of the American Hockey League.
-
C.
Boston T
Boston T is the public rapid transit system serving the Greater Boston area, operated by the Massachusetts Bay Transportation Authority (MBTA).
-
D.
BOL
BOL is the three-letter ISO 3166-1 alpha-3 country code assigned to Bolivia.
-
E.
BJ Boston
BJ Boston is an American professional basketball player and former five-star high school recruit known for his scoring ability on the wing.
- 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_69d6aa5a4c4881908f39be6efe5981e5 |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d6dfcd19648190882380d2c90be486 |
completed | April 8, 2026, 11:07 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d96bcd8c0c8190a0fad6a85b5604bb |
completed | April 10, 2026, 9:29 p.m. |
Created at: April 8, 2026, 9:04 p.m.