Triple
T29655007
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Colossus |
E750240
|
entity |
| Predicate | movementTrait |
P159654
|
FINISHED |
| Object | can traverse cliffs |
—
|
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: can traverse cliffs | Statement: [Colossus, movementTrait, can traverse cliffs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: movementTrait Context triple: [Colossus, movementTrait, can traverse cliffs]
-
A.
movementCharacteristic
Indicates how an entity moves or behaves in motion, such as its style, pattern, or quality of movement.
-
B.
movementType
Indicates the manner or mode in which an entity moves or is moved from one place or state to another.
-
C.
movementCapability
chosen
Indicates the ability or potential of an entity to move or be moved in a particular way or under certain conditions.
-
D.
movementRole
Indicates the specific function or capacity an entity has within a movement or motion-related activity (e.g., mover, path, source, or goal).
-
E.
movementFunction
Indicates a functional or operational role related to enabling, controlling, or characterizing movement between entities.
- 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_69f0d6226fe881908819197c9ef9ee04 |
completed | April 28, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69f6afebd7ec8190ab696f363d84abf0 |
completed | May 3, 2026, 2:16 a.m. |
| PD | Predicate disambiguation | batch_69f6aca204148190850a3dc325bc07b7 |
completed | May 3, 2026, 2:02 a.m. |
Created at: April 28, 2026, 6:54 p.m.