Triple
T4160067
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Torrejón Air Base |
E91509
|
entity |
| Predicate | proximityToCapital |
P33891
|
FINISHED |
| Object | close to Madrid |
—
|
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: close to Madrid | Statement: [Torrejón Air Base, proximityToCapital, close to Madrid]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: proximityToCapital Context triple: [Torrejón Air Base, proximityToCapital, close to Madrid]
-
A.
distanceFromCapital
Indicates the measured distance between a given location and the capital city of its corresponding region or country.
-
B.
stateCapitalProximity
Indicates the spatial closeness or distance between a state’s capital city and another specified location.
-
C.
regionCapitalNearby
Indicates that a capital city of a region is located close to the referenced place or entity.
-
D.
countryCapitalNearby
chosen
Indicates that a country’s capital city is geographically close to a specified location or entity.
-
E.
proximityToLandmark
Indicates a spatial relationship where one entity is located near or close to a specified landmark.
- 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_69aed9626ebc8190a39de631788bea3e |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69af0321eee88190871c1d4bf44a5007 |
completed | March 9, 2026, 5:28 p.m. |
| PD | Predicate disambiguation | batch_69af018dc90c8190a754b1bfbc802e80 |
completed | March 9, 2026, 5:21 p.m. |
Created at: March 9, 2026, 3:44 p.m.