Triple
T14962393
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Great War against the dead |
E373093
|
entity |
| Predicate | decisiveAct |
P23903
|
FINISHED |
| Object | Arya Stark kills the Night King |
—
|
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: Arya Stark kills the Night King | Statement: [Great War against the dead, decisiveAct, Arya Stark kills the Night King]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: decisiveAct Context triple: [Great War against the dead, decisiveAct, Arya Stark kills the Night King]
-
A.
decisiveFor
chosen
Indicates that one entity plays a determining or conclusive role in bringing about a particular outcome, decision, or state of another entity.
-
B.
decisive
Indicates that one entity makes a conclusive choice or determination that resolves a situation or outcome between entities.
-
C.
decides
Indicates that an entity makes a choice or determination between options, often resolving uncertainty or selecting a course of action.
-
D.
decisiveness
Indicates the degree to which an entity consistently makes timely, firm choices without excessive hesitation or reversal.
-
E.
decisionEffect
Indicates that one decision leads to, influences, or determines a particular outcome or consequence.
- 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_69d85cca979481908747d2a81eba1cea |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded6cece6881908cd8c8fe41583bee |
completed | April 15, 2026, 12:07 a.m. |
| PD | Predicate disambiguation | batch_69de9a5d995881909e33658f5aea5582 |
completed | April 14, 2026, 7:49 p.m. |
Created at: April 10, 2026, 2:40 a.m.