Triple
T1991341
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Terminal E |
E43257
|
entity |
| Predicate | hasConnectionTo |
P845
|
FINISHED |
| Object | Terminal D |
unclear NED1
|
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: Terminal D | Statement: [Terminal E, hasConnectionTo, Terminal D]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Terminal D Context triple: [Terminal E, hasConnectionTo, Terminal D]
-
A.
Terminal D
Terminal D is one of the passenger terminals at Luis Muñoz Marín International Airport in Puerto Rico, serving commercial air travelers with check-in, security, boarding gates, and related airport services.
-
B.
Terminal D
Terminal D is one of the main passenger terminals at Sheremetyevo International Airport in Moscow, serving numerous international and domestic flights.
-
C.
Terminal D
Terminal D is one of the passenger terminals at New York City's LaGuardia Airport, serving as a concourse for airline check-in, security, boarding, and arrivals.
-
D.
Terminal D
Terminal D is the international terminal at Dallas/Fort Worth International Airport, serving as a major hub for long-haul and global flights with extensive passenger amenities.
-
E.
Terminal D
Terminal D is one of the passenger terminals at Philadelphia International Airport, serving domestic flights with various airlines and amenities.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide. chosen
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_69a88714cf2c819081644be450b8356e |
completed | March 4, 2026, 7:25 p.m. |
| NER | Named-entity recognition | batch_69abb8451fe8819093531052f4533c36 |
completed | March 7, 2026, 5:31 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae2705752c81908054e8e0e426e86d |
completed | March 9, 2026, 1:48 a.m. |
Created at: March 4, 2026, 7:37 p.m.