Triple
T2059842
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Heathrow Terminal 5 |
E45765
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | Terminal 5A |
E88066
|
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 5A | Statement: [Heathrow Terminal 5, hasPart, Terminal 5A]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Terminal 5A Context triple: [Heathrow Terminal 5, hasPart, Terminal 5A]
-
A.
Terminal 5
chosen
Terminal 5 is a major, modern passenger terminal at London Heathrow Airport primarily serving British Airways and Iberia flights.
-
B.
Terminal 5
Terminal 5 is one of the passenger terminals at José Martí International Airport in Havana, Cuba, serving specific airlines and routes.
-
C.
Terminal 5
Terminal 5 is one of the passenger terminals at Los Angeles International Airport, serving a mix of domestic and some international flights with various airlines and amenities.
-
D.
Terminal 5
Terminal 5 is a dedicated passenger terminal at Rome’s Leonardo da Vinci–Fiumicino Airport, primarily used for certain international and long-haul flights.
-
E.
Terminal 5
Terminal 5 is a passenger terminal facility at Mehrabad International Airport in Tehran, Iran.
- 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_69a8891a19508190a12ef1e192308dcb |
completed | March 4, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69abb9cfdac88190b8b7af1bfea6a78e |
completed | March 7, 2026, 5:38 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae2014da048190902b2a23574d34ef |
completed | March 9, 2026, 1:19 a.m. |
Created at: March 4, 2026, 7:40 p.m.