Triple
T20387596
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Prime Timeline |
E497997
|
entity |
| Predicate | divergesFromAtEvent |
P127849
|
FINISHED |
| Object | destruction of the USS Kelvin |
—
|
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: destruction of the USS Kelvin | Statement: [Prime Timeline, divergesFromAtEvent, destruction of the USS Kelvin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: divergesFromAtEvent Context triple: [Prime Timeline, divergesFromAtEvent, destruction of the USS Kelvin]
-
A.
followsInDivergence
Indicates that one entity comes after another specifically within a divergent or branching sequence, path, or process.
-
B.
divergesAt
Indicates that a process, function, or behavior fails to converge or terminate at a specific point or under specific conditions.
-
C.
posedAtEvent
Indicates that an entity assumed a particular pose or posture during a specified event.
-
D.
divertedFrom
chosen
Indicates that something has been redirected or rerouted away from its original or intended course, destination, or target.
-
E.
laterRelatedEvent
Indicates that one event is temporally related to another by occurring at a later time.
- 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_69e0b4a71ebc8190b153a36c738730f4 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6790c935881908f901d058e6a83a9 |
completed | April 20, 2026, 7:05 p.m. |
| PD | Predicate disambiguation | batch_69e57648be3c81908256838228cabf5c |
completed | April 20, 2026, 12:41 a.m. |
Created at: April 16, 2026, 11:28 a.m.