Triple
T20196773
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 924 Gilman Street |
E493104
|
entity |
| Predicate | violencePolicy |
P20272
|
FINISHED |
| Object | anti-violence |
—
|
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: anti-violence | Statement: [924 Gilman Street, violencePolicy, anti-violence]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: violencePolicy Context triple: [924 Gilman Street, violencePolicy, anti-violence]
-
A.
containsViolence
Indicates that the subject includes, depicts, or involves acts of physical harm, aggression, or violent behavior.
-
B.
violenceLevel
Indicates the degree or intensity of violent behavior, actions, or content present in or associated with an entity.
-
C.
viewOnViolence
chosen
Indicates an entity’s stance, opinion, or attitude toward the use of violence.
-
D.
victimCountPolicy
Indicates the rule or criterion used to determine how victims are counted or classified in a given context.
-
E.
justifiesViolenceThrough
Indicates that one party legitimizes or defends the use of violence by appealing to, or reasoning through, another factor, belief, or circumstance.
- 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_69da6268a034819081cbd9ea5a1c9475 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e66ad99d50819090ddb7b546c65321 |
completed | April 20, 2026, 6:05 p.m. |
| PD | Predicate disambiguation | batch_69e55b14c9d8819095453d0504d9222f |
completed | April 19, 2026, 10:45 p.m. |
Created at: April 11, 2026, 11:37 p.m.