Triple
T32073472
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Force de frappe |
E819077
|
entity |
| Predicate | formerLandBasedSite |
P126626
|
FINISHED |
| Object | Plateau d'Albion |
—
|
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: Plateau d'Albion | Statement: [Force de frappe, formerLandBasedSite, Plateau d'Albion]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formerLandBasedSite Context triple: [Force de frappe, formerLandBasedSite, Plateau d'Albion]
-
A.
formerSiteOf
Indicates that a location previously hosted or contained something (such as a structure, organization, or event) that is no longer present there.
-
B.
formerMilitaryBase
chosen
Indicates that a location was previously used as a military base but no longer serves that function.
-
C.
formerLandBasedMissile
Indicates that something was previously a land-based missile but no longer holds that status.
-
D.
wasLandingSiteOf
Indicates that a location served as the site where a landing event (such as a spacecraft, aircraft, or vehicle) took place.
-
E.
wasLandingSiteIn
Indicates that a specific landing event occurred at or within the location denoted by the related entity.
- 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_69f348fecc088190af1470afe5a969f0 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69ff63e6b61081909c648bf0ff279481 |
completed | May 9, 2026, 4:42 p.m. |
| PD | Predicate disambiguation | batch_69ff6381867881908ae0545df4b71df5 |
completed | May 9, 2026, 4:40 p.m. |
Created at: May 1, 2026, 12:23 a.m.