Triple
T17974289
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Treasury Islands |
E449425
|
entity |
| Predicate | airfieldUsedBy |
P95531
|
FINISHED |
| Object | Allied aircraft |
—
|
LITERAL 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: Allied aircraft | Statement: [Treasury Islands, airfieldUsedBy, Allied aircraft]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: airfieldUsedBy Context triple: [Treasury Islands, airfieldUsedBy, Allied aircraft]
-
A.
airfieldRole
Indicates the functional role or operational purpose that an airfield serves within a broader system or context.
-
B.
airfieldBuilt
Indicates that an airfield has been constructed or established, typically specifying who built it, where, and/or when.
-
C.
containsAirfield
Indicates that a location or area includes at least one airfield within its boundaries.
-
D.
isPrimaryRunwayOf
Indicates that a runway serves as the main or principal runway for a particular airport or airfield.
-
E.
operatedAirfields
chosen
Indicates that an entity had operational control over and actively used specific airfields.
- 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_69d8b9f9927c8190a006110c8b996e61 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4b1fe24808190baa11739f4d1095f |
completed | April 19, 2026, 10:44 a.m. |
| PD | Predicate disambiguation | batch_69e3f8fa62688190a5d5c361ab896256 |
completed | April 18, 2026, 9:34 p.m. |
Created at: April 10, 2026, 10:22 a.m.