Triple
T23965553
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1st Airborne Reconnaissance Squadron |
E604067
|
entity |
| Predicate | gathersInformationOn |
P41259
|
FINISHED |
| Object | enemy positions |
—
|
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: enemy positions | Statement: [1st Airborne Reconnaissance Squadron, gathersInformationOn, enemy positions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: gathersInformationOn Context triple: [1st Airborne Reconnaissance Squadron, gathersInformationOn, enemy positions]
-
A.
collectsInformationOn
chosen
Indicates that one entity gathers or acquires data, facts, or details about another entity.
-
B.
providesInformationIn
Indicates that one entity supplies or conveys information within or through another entity or context.
-
C.
collectsDataFor
Indicates that one entity gathers or records data on behalf of, or for the benefit of, another entity.
-
D.
providedInformationOn
Indicates that one entity supplied or communicated specific information or details to another entity.
-
E.
gathering
Indicates that one or more entities are coming together or being brought together into a group at a particular time or place.
- 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_69e29543019c8190872462e593cc50b4 |
completed | April 17, 2026, 8:17 p.m. |
| NER | Named-entity recognition | batch_69f1d1d7077881909d4774b7040cd722 |
completed | April 29, 2026, 9:39 a.m. |
| PD | Predicate disambiguation | batch_69f161578d54819084a8b35496299993 |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 9:24 p.m.