Triple
T36937376
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kino der Toten |
E913654
|
entity |
| Predicate | teleporterCooldown |
P63769
|
FINISHED |
| Object | 45 seconds (approximate) |
—
|
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: 45 seconds (approximate) | Statement: [Kino der Toten, teleporterCooldown, 45 seconds (approximate)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: teleporterCooldown Context triple: [Kino der Toten, teleporterCooldown, 45 seconds (approximate)]
-
A.
canTeleport
Indicates that an entity has the ability to instantaneously move itself or something else from one location to another without traversing the space in between.
-
B.
cooldown
chosen
Indicates that an entity must wait a specified period of time before performing the same action or a related action again.
-
C.
timeTravelActivationSpeed
Indicates the speed or rate at which a time travel mechanism or process becomes active once initiated.
-
D.
timeTravelTrigger
Indicates an event, condition, or mechanism that initiates or enables time travel to occur.
-
E.
travelTimeThroughWormholeTo
Indicates the duration required for an entity to traverse a wormhole and reach a specified destination.
- 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_69f76e8a6a5c81909c1febf32bf3fe23 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fb34e5576881909394355c8ec6ddd2 |
completed | May 6, 2026, 12:32 p.m. |
| PD | Predicate disambiguation | batch_69fb2f6171e88190bf1e0ee6a644b6a9 |
completed | May 6, 2026, 12:09 p.m. |
Created at: May 3, 2026, 4:13 p.m.