Triple
T28038364
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Source |
E708471
|
entity |
| Predicate | physicsEngine |
P69440
|
FINISHED |
| Object | Havok |
—
|
NE NERFINISHED |
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: Havok | Statement: [Source, physicsEngine, Havok]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: physicsEngine Context triple: [Source, physicsEngine, Havok]
-
A.
physicsFeature
Indicates that one entity possesses or exhibits a specific physical or physics-related property, behavior, or characteristic in relation to another.
-
B.
supportsPhysics
chosen
Indicates that one entity provides the necessary capabilities or features for another entity to handle, simulate, or work with physical behaviors or physics-based interactions.
-
C.
collisionSystem
Indicates a physical interaction where two or more entities impact or collide with each other within a defined system or environment.
-
D.
collisionDomain
Indicates that two or more network entities share the same collision domain, meaning their transmissions can interfere and cause packet collisions with each other.
-
E.
physicsModelTested
Indicates that a physics model has been subjected to testing or evaluation, typically to assess its validity or performance.
- 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_69ef9b6cf538819094a633ffa67afec1 |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69f63f2e1a248190a41f02f91e8c1183 |
completed | May 2, 2026, 6:15 p.m. |
| PD | Predicate disambiguation | batch_69f63710d17c819084cfe96e6df334fd |
completed | May 2, 2026, 5:40 p.m. |
Created at: April 27, 2026, 8:23 p.m.