Triple
T1377840
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Barton Swing Aqueduct |
E29265
|
entity |
| Predicate | movementMechanism |
P3705
|
FINISHED |
| Object | swings horizontally |
—
|
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: swings horizontally | Statement: [Barton Swing Aqueduct, movementMechanism, swings horizontally]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: movementMechanism Context triple: [Barton Swing Aqueduct, movementMechanism, swings horizontally]
-
A.
movementType
Indicates the manner or mode in which an entity moves or is moved from one place or state to another.
-
B.
movementCharacteristic
Indicates how an entity moves or behaves in motion, such as its style, pattern, or quality of movement.
-
C.
movementCause
Indicates that one entity’s action or event is the cause of another entity’s movement or change in location.
-
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.
transitionMechanismUsedWith
chosen
Indicates that a particular transition or change from one state to another is carried out using a specified mechanism or method.
- 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_69a498d883a48190bfdca525296ef7ee |
completed | March 1, 2026, 7:51 p.m. |
| NER | Named-entity recognition | batch_69a4c3173548819082aec7c1af9c577c |
completed | March 1, 2026, 10:52 p.m. |
| PD | Predicate disambiguation | batch_69a4befcabdc8190a9f05d002603f81c |
completed | March 1, 2026, 10:34 p.m. |
Created at: March 1, 2026, 7:59 p.m.