Triple
T24431191
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ashley Williams |
E616004
|
entity |
| Predicate | survivesVirmireIf |
P156107
|
FINISHED |
| Object | player chooses to save Ashley |
—
|
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: player chooses to save Ashley | Statement: [Ashley Williams, survivesVirmireIf, player chooses to save Ashley]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: survivesVirmireIf Context triple: [Ashley Williams, survivesVirmireIf, player chooses to save Ashley]
-
A.
survivesWith
Indicates that one entity continues to live, endure, or remain viable in the presence, context, or company of another entity.
-
B.
hasSurvivors
Indicates that one or more entities continue to exist or remain alive after a particular event, condition, or incident.
-
C.
survivesIn
Indicates that an entity remains alive, functional, or intact within a specified environment, condition, or context.
-
D.
survivesFor
Indicates that one entity continues to exist, endure, or remain functional for a specified duration or period.
-
E.
survivesBy
Indicates that one entity continues to live or exist after another entity has died or ceased to exist.
- 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_69e2d7eadb248190a867130fe45f0388 |
completed | April 18, 2026, 1:01 a.m. |
| NER | Named-entity recognition | batch_69f29782a4a0819087cb7ba399371520 |
completed | April 29, 2026, 11:42 p.m. |
| PD | Predicate disambiguation | batch_69f287d3237c819099559c00f83131d8 |
completed | April 29, 2026, 10:36 p.m. |
| PDg | Predicate description generation | batch_69f28f4d978c81908310c01def2514cc |
completed | April 29, 2026, 11:07 p.m. |
Created at: April 18, 2026, 2:16 a.m.