Triple
T36914733
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | BAA |
E913013
|
entity |
| Predicate | requiredToDivestAirport |
P201672
|
FINISHED |
| Object | Gatwick Airport |
—
|
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: Gatwick Airport | Statement: [BAA, requiredToDivestAirport, Gatwick Airport]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: requiredToDivestAirport Context triple: [BAA, requiredToDivestAirport, Gatwick Airport]
-
A.
appliesToAirportUse
Indicates that something (such as a rule, restriction, or provision) is specifically applicable to the use or operation of an airport.
-
B.
appliesToAirport
Indicates that something is relevant, valid, or specifically intended for use at a particular airport.
-
C.
designedForAirports
Indicates that something is specifically created or optimized to be used in or meet the needs of airports.
-
D.
requiresETOPS
Indicates that one entity can only operate, proceed, or be valid if Extended-range Twin-engine Operational Performance Standards (ETOPS) certification or compliance is in place for the associated aircraft, route, or operation.
-
E.
airfieldDecommissioned
Indicates that an airfield has been officially taken out of service and is no longer used for regular aviation operations.
- F. None of above. chosen
Provenance (4 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_69f76e879768819085c2fb31a6a5b44b |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a00119d821c8190874786391b27ef23 |
completed | May 10, 2026, 5:03 a.m. |
| PD | Predicate disambiguation | batch_6a001143fb6881909ac0ae8bfea04351 |
completed | May 10, 2026, 5:01 a.m. |
| PDg | Predicate description generation | batch_6a00119ca1d881909a72a9c3b937c43c |
completed | May 10, 2026, 5:03 a.m. |
Created at: May 3, 2026, 4:13 p.m.