Triple
T24916356
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | HERA |
E623995
|
entity |
| Predicate | alsoCollided |
P12942
|
FINISHED |
| Object | positron–proton |
—
|
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: positron–proton | Statement: [HERA, alsoCollided, positron–proton]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: alsoCollided Context triple: [HERA, alsoCollided, positron–proton]
-
A.
marksCollisionBetween
Indicates a recorded event or state where two or more entities have come into contact or collided with each other.
-
B.
collidesWith
chosen
Indicates that two entities come into contact with each other in space, typically implying an impact or physical intersection of their paths or volumes.
-
C.
sharesColliderWith
Indicates that two entities are configured to use or occupy the same physics collider, causing them to share collision detection behavior.
-
D.
collisionAttackKnown
Indicates that a collision-based attack method or vulnerability is known or has been discovered.
-
E.
collisionResult
Indicates the outcome or consequence that occurs when two or more entities collide.
- 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_69e2fac889c081908e9ff686cb428e5a |
completed | April 18, 2026, 3:30 a.m. |
| NER | Named-entity recognition | batch_69f4238c52488190a58b1191f4dc3373 |
completed | May 1, 2026, 3:52 a.m. |
| PD | Predicate disambiguation | batch_69f4210130d08190ae30b7943f7a0bbc |
completed | May 1, 2026, 3:41 a.m. |
Created at: April 18, 2026, 5:28 a.m.