Triple
T19174540
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Skylink |
E469405
|
entity |
| Predicate | hasStationAt |
P105426
|
FINISHED |
| Object | Terminal E |
—
|
NE NERFINISHED |
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 E | Statement: [Skylink, hasStationAt, Terminal E]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Terminal E Context triple: [Skylink, hasStationAt, Terminal E]
-
A.
Terminal E
Terminal E is one of the passenger terminals at Sheremetyevo International Airport in Moscow, serving international flights with modern facilities and connections to adjacent terminals.
-
B.
Terminal E
Terminal E is the international terminal at Boston Logan International Airport, serving most of the airport’s overseas flights and customs operations.
-
C.
Terminal E
Terminal E is one of the passenger terminals at Dallas/Fort Worth International Airport, serving various domestic and some international flights with multiple gates and amenities.
-
D.
Terminal E
Terminal E is an international satellite terminal at Zurich Airport primarily serving long-haul and non-Schengen flights.
-
E.
Terminal E
Terminal E is one of the passenger terminals at Philadelphia International Airport, primarily serving domestic airline operations and regional flights.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide. chosen
Provenance (2 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_69d8dd09d5a081909ae43c286651ae5a |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5f166d3888190adaf6dc8531a8ed1 |
completed | April 20, 2026, 9:27 a.m. |
Created at: April 10, 2026, 12:06 p.m.