Triple
T23481405
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Detective Lieutenant Mike Rogo |
E570413
|
entity |
| Predicate | survivalGoal |
P39497
|
FINISHED |
| Object | escape overturned ship |
—
|
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: escape overturned ship | Statement: [Detective Lieutenant Mike Rogo, survivalGoal, escape overturned ship]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: survivalGoal Context triple: [Detective Lieutenant Mike Rogo, survivalGoal, escape overturned ship]
-
A.
survivalTheme
Indicates that the relationship or situation centers on the struggle to stay alive or endure extreme hardship.
-
B.
survivingUse
Indicates that one entity continues to make use of another entity or resource after an event that could have ended or invalidated that use.
-
C.
survivingFrom
Indicates that one entity continues to live, exist, or remain after another related entity has ended, disappeared, or ceased to exist.
-
D.
survivesFor
Indicates that one entity continues to exist, endure, or remain functional for a specified duration or period.
-
E.
safetyGoal
chosen
Indicates that an entity is associated with a specific safety objective or target condition intended to prevent harm or reduce risk.
- 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_69e245af8a88819084f2704f6d265a92 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1a75002008190b02fbffd94e5e8b1 |
completed | April 29, 2026, 6:38 a.m. |
| PD | Predicate disambiguation | batch_69f0620ac3608190b36916261ea50f54 |
completed | April 28, 2026, 7:30 a.m. |
Created at: April 17, 2026, 6:03 p.m.