Triple
T30650024
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Back in Crime |
E780228
|
entity |
| Predicate | timeTravelInvolves |
P125181
|
FINISHED |
| Object | going back to the past to prevent serial murders |
—
|
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: going back to the past to prevent serial murders | Statement: [Back in Crime, timeTravelInvolves, going back to the past to prevent serial murders]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: timeTravelInvolves Context triple: [Back in Crime, timeTravelInvolves, going back to the past to prevent serial murders]
-
A.
timeTravelInvolvement
Indicates that an entity participates in, is affected by, or is otherwise involved in an instance of time travel.
-
B.
timeTravelType
Indicates the specific method or mechanism by which time travel is carried out in a given context.
-
C.
timeTravelPurpose
chosen
Indicates that an instance of time travel is undertaken with a specific goal, motive, or intended outcome in mind.
-
D.
timeTravelMethod
Indicates the specific mechanism or technique by which an entity performs or experiences time travel.
-
E.
timeTravelTo
Indicates traveling from one point in time to another, typically different, point in 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_69f224a5d2b481908a6853cd0138e2d7 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f68a975e1c81909d7424ae7af3410b |
completed | May 2, 2026, 11:36 p.m. |
| PD | Predicate disambiguation | batch_69f6861170d08190bb98be609d436f84 |
completed | May 2, 2026, 11:17 p.m. |
Created at: April 29, 2026, 8:30 p.m.