Triple
T7144612
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ATL |
E166530
|
entity |
| Predicate | hasConcourse |
P1656
|
FINISHED |
| Object | Concourse A |
E168343
|
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: Concourse A | Statement: [ATL, hasConcourse, Concourse A]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Concourse A Context triple: [ATL, hasConcourse, Concourse A]
-
A.
Concourse A
Concourse A is a major passenger terminal facility at Dubai International Airport, primarily serving long-haul international flights and Emirates’ Airbus A380 operations.
-
B.
Concourse A
chosen
Concourse A is one of the main passenger terminal concourses at Hartsfield–Jackson Atlanta International Airport, serving numerous domestic airline gates and amenities.
-
C.
Concourse A
Concourse A is one of the passenger concourses at Memphis International Airport, housing gates and facilities for airline operations and travelers.
-
D.
Concourse A
Concourse A is one of the passenger terminal concourses at Richmond International Airport, serving as a boarding area for multiple airline gates and flights.
-
E.
Concourse A
Concourse A is a major passenger concourse at Incheon International Airport in South Korea, serving international flights with extensive boarding gates and modern facilities.
- 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_69c6888579d481909e05a8d6b81bf733 |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6e7d1652c8190973edceab55f04bc |
completed | March 27, 2026, 8:25 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7ad9c9f508190b36ff96b586a7726 |
completed | March 28, 2026, 10:29 a.m. |
Created at: March 27, 2026, 2:46 p.m.