Triple
T28639698
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Safe House |
E724886
|
entity |
| Predicate | protagonistCooperatesWith |
P148762
|
FINISHED |
| Object | police |
—
|
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: police | Statement: [Safe House, protagonistCooperatesWith, police]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: protagonistCooperatesWith Context triple: [Safe House, protagonistCooperatesWith, police]
-
A.
coProtagonist
Indicates that two or more entities share the primary leading role together in the same narrative work.
-
B.
cooperateThrough
Indicates that entities work together or coordinate their actions by means of a specific intermediary, method, or channel.
-
C.
helpsProtagonistWith
Indicates that one entity assists the protagonist in performing, achieving, or dealing with something specified by the other entity.
-
D.
involvesCooperation
chosen
Indicates that the related entities participate together in a shared activity or goal that requires mutual assistance or coordinated effort.
-
E.
protagonistAlly
Indicates that one entity serves as an ally, supporter, or close associate of the story’s main protagonist.
- 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_69f01d8328c48190bc0e5f9b9b848582 |
completed | April 28, 2026, 2:37 a.m. |
| NER | Named-entity recognition | batch_69f658ee40088190b71e1219407690d0 |
completed | May 2, 2026, 8:05 p.m. |
| PD | Predicate disambiguation | batch_69f65760fd3081908ffe014a5e2bf069 |
completed | May 2, 2026, 7:58 p.m. |
Created at: April 28, 2026, 4:43 a.m.