Triple
T4338870
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kevin Lynch |
E97529
|
entity |
| Predicate | associatedWithPrisonProtest |
P56130
|
FINISHED |
| Object | blanket protest |
—
|
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: blanket protest | Statement: [Kevin Lynch, associatedWithPrisonProtest, blanket protest]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedWithPrisonProtest Context triple: [Kevin Lynch, associatedWithPrisonProtest, blanket protest]
-
A.
teamDuringProtest
Indicates that two or more entities are part of the same team or organized group specifically in the context of a protest event.
-
B.
notableProtest
Indicates that an entity is recognized for having led, organized, or been centrally involved in a significant protest or demonstration.
-
C.
postPrisonOccupation
Indicates the type of work or occupation a person engages in after being released from prison.
-
D.
protests
Indicates that an entity publicly expresses opposition or disapproval toward another entity, action, or situation.
-
E.
locationOfNotableProtest
Indicates the place where a significant or notable protest event occurred.
- F. None of above. chosen
Provenance (4 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_69b3454662a481908fbcd0bbfaa3a0a4 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b3516dffb48190878f81ffe71a5e82 |
completed | March 12, 2026, 11:51 p.m. |
| PD | Predicate disambiguation | batch_69b34f4fe1c481908d6d66e15697c04b |
completed | March 12, 2026, 11:42 p.m. |
| PDg | Predicate description generation | batch_69b350d1649881908fa6556d875a8b4d |
completed | March 12, 2026, 11:48 p.m. |
Created at: March 12, 2026, 11:14 p.m.