Triple
T29549068
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dr. Sam Beckett |
E749710
|
entity |
| Predicate | temporalDisplacement |
P81104
|
FINISHED |
| Object | late 20th century to various points in the past |
—
|
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: late 20th century to various points in the past | Statement: [Dr. Sam Beckett, temporalDisplacement, late 20th century to various points in the past]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: temporalDisplacement Context triple: [Dr. Sam Beckett, temporalDisplacement, late 20th century to various points in the past]
-
A.
temporal
Indicates a relationship that situates one event, state, or entity in time relative to another (e.g., before, after, or during).
-
B.
timeJump
chosen
Indicates a discontinuous transition of an entity from one point in time to another, skipping the intervening duration.
-
C.
timeTravelDirection
Indicates the temporal direction in which time travel occurs, such as moving into the past or into the future.
-
D.
timeTravelType
Indicates the specific method or mechanism by which time travel is carried out in a given context.
-
E.
timeTravelElement
Indicates that the situation, event, or narrative involves an element of time travel, such as moving between different points in time or altering temporal sequences.
- 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_69f0bd48691081908cecad39bac591e0 |
completed | April 28, 2026, 1:59 p.m. |
| NER | Named-entity recognition | batch_69f674e06c9481909ed0ea736408f0d7 |
completed | May 2, 2026, 10:04 p.m. |
| PD | Predicate disambiguation | batch_69f673c4abec8190bc2379e66f4af0a9 |
completed | May 2, 2026, 9:59 p.m. |
Created at: April 28, 2026, 5:10 p.m.