Triple
T23424927
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Probot |
E560767
|
entity |
| Predicate | hasCollaborator |
P10645
|
FINISHED |
| Object | Snake |
—
|
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: Snake | Statement: [Probot, hasCollaborator, Snake]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Snake Context triple: [Probot, hasCollaborator, Snake]
-
A.
Snake
Snake is a large, spiraling steel sculpture by Richard Serra that forms part of his monumental installation "The Matter of Time" at the Guggenheim Museum Bilbao.
-
B.
Snake
chosen
Snake is a legless, carnivorous reptile known for its elongated body, flexible jaw, and often venomous bite, found in diverse habitats worldwide.
-
C.
Snake
"Snake" is a raw, intense track by PJ Harvey from her critically acclaimed 1993 album "Rid of Me."
-
D.
Snake
Snake is the central protagonist of the 1993 action film "Airborne," around whom the movie’s primary conflicts and narrative developments revolve.
-
E.
Snake
Snake is a classic mobile arcade game in which the player guides a growing line to collect items while avoiding collisions with walls and its own tail.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e2454cb1108190ab21ada5411a7146 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1a54951688190a3c5382971af3e41 |
completed | April 29, 2026, 6:29 a.m. |
Created at: April 17, 2026, 5:47 p.m.