Triple
T36517907
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rand Paul presidential campaign, 2016 |
E900096
|
entity |
| Predicate | positionOnSurveillance |
P89137
|
FINISHED |
| Object | opposed NSA bulk data collection |
—
|
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: opposed NSA bulk data collection | Statement: [Rand Paul presidential campaign, 2016, positionOnSurveillance, opposed NSA bulk data collection]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: positionOnSurveillance Context triple: [Rand Paul presidential campaign, 2016, positionOnSurveillance, opposed NSA bulk data collection]
-
A.
positionOnSecurity
chosen
Indicates the stance, opinion, or policy an entity holds regarding security-related issues or measures.
-
B.
surveillanceArea
Indicates the area or region that is monitored or observed by a surveillance system or agent.
-
C.
surveillanceCondition
Indicates the specific circumstances or criteria under which surveillance or monitoring of an entity is required, active, or applicable.
-
D.
positionOnCrime
Indicates a stance, opinion, or policy position that an entity holds regarding crime or crime-related issues.
-
E.
positionInMission
Indicates the specific role, rank, or placement an entity holds within a particular mission or operation.
- 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_69f76e5dada881909da2d34bc7a9202a |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69ffa9677be08190852c8ef6c2545fed |
completed | May 9, 2026, 9:38 p.m. |
| PD | Predicate disambiguation | batch_69ffa6570e2c8190a9d7b37f12b91d9a |
completed | May 9, 2026, 9:25 p.m. |
Created at: May 3, 2026, 4:11 p.m.