Triple
T7254190
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bull Connor |
E157676
|
entity |
| Predicate | usedPoliceDogsAgainst |
P16495
|
FINISHED |
| Object | civil rights protesters |
—
|
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: civil rights protesters | Statement: [Bull Connor, usedPoliceDogsAgainst, civil rights protesters]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedPoliceDogsAgainst Context triple: [Bull Connor, usedPoliceDogsAgainst, civil rights protesters]
-
A.
usesCaninesFor
Indicates a relationship where an entity employs or relies on its canine teeth for a particular function or activity.
-
B.
usedMilitaryAnimal
Indicates that an entity employed an animal for military purposes, such as in combat, transport, communication, or support roles.
-
C.
barkUsedFor
Indicates that the bark of something is utilized for a particular purpose or function.
-
D.
usedByLawEnforcementModel
Indicates that something is employed or utilized by law enforcement agencies or personnel, typically as a tool, method, or model in their operations or decision-making.
-
E.
usedAnimal
chosen
Indicates that one entity employed or exploited an animal for a particular purpose or activity.
- 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_69c6882d81d4819085f7ff862951ee4f |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6ea9f55b4819081a43e7a01eda154 |
completed | March 27, 2026, 8:37 p.m. |
| PD | Predicate disambiguation | batch_69c6e7666ffc81908bf643d8257e6337 |
completed | March 27, 2026, 8:24 p.m. |
Created at: March 27, 2026, 2:56 p.m.