Triple
T32412234
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Liverpool (Speke) Airport |
E828255
|
entity |
| Predicate | sharedAirfieldWith |
P25487
|
FINISHED |
| Object | RAF Speke |
—
|
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: RAF Speke | Statement: [Liverpool (Speke) Airport, sharedAirfieldWith, RAF Speke]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sharedAirfieldWith Context triple: [Liverpool (Speke) Airport, sharedAirfieldWith, RAF Speke]
-
A.
airfieldSharedWith
chosen
Indicates that two or more entities use the same airfield facilities or infrastructure for their operations.
-
B.
sharesAirportWith
Indicates that two entities use or are associated with the same airport.
-
C.
isJointUseAirport
Indicates that an airport facility is shared and used jointly by multiple organizations or authorities, such as civilian and military operators.
-
D.
sharesAircraftWith
Indicates that two or more entities use, operate, or are associated with the same aircraft.
-
E.
runwaySharedBy
Indicates that the same runway is used jointly by multiple entities, such as aircraft, airlines, or airports.
- F. None of above.
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_69f34919f300819092b541c6277cd68a |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69ff5285ed74819097e6e2a9084a079a |
completed | May 9, 2026, 3:28 p.m. |
| PD | Predicate disambiguation | batch_69ff51fbe28881908ac8417dff9db81a |
completed | May 9, 2026, 3:25 p.m. |
Created at: May 1, 2026, 12:53 a.m.