Triple
T35647289
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Confederado territory |
E1030044
|
entity |
| Predicate | safetyControlledBy |
P97456
|
FINISHED |
| Object | park technicians |
—
|
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: park technicians | Statement: [Confederado territory, safetyControlledBy, park technicians]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: safetyControlledBy Context triple: [Confederado territory, safetyControlledBy, park technicians]
-
A.
isControlledUnder
Indicates that one entity is subject to regulatory, legal, or authoritative control exercised by another entity or governing framework.
-
B.
securedControlOver
Indicates that one entity has successfully obtained and established authoritative control or dominance over another entity or resource.
-
C.
isUnderControlOf
chosen
Indicates that one entity is subject to the authority, direction, or governance of another entity.
-
D.
controlledIn
Indicates that one entity exercised control, authority, or governance over another entity within a specific context or domain.
-
E.
effectControlledBy
Indicates that the occurrence, magnitude, or outcome of one effect is regulated, determined, or constrained by another specified factor or agent.
- 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_69f76e0938088190a8f199631e97dec3 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7a34f8ee08190a040304635539a8f |
completed | May 3, 2026, 7:34 p.m. |
| PD | Predicate disambiguation | batch_69f7a06f125c8190843af194f042a465 |
completed | May 3, 2026, 7:22 p.m. |
Created at: May 3, 2026, 4:05 p.m.