Triple
T37351545
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Engine Arm |
E927335
|
entity |
| Predicate | hasCrossingStructure |
P48527
|
FINISHED |
| Object | Engine Arm Aqueduct |
—
|
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: Engine Arm Aqueduct | Statement: [Engine Arm, hasCrossingStructure, Engine Arm Aqueduct]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCrossingStructure Context triple: [Engine Arm, hasCrossingStructure, Engine Arm Aqueduct]
-
A.
crossingStructure
chosen
Indicates that one entity serves as a structure enabling passage across or over another entity, such as a bridge, tunnel, or overpass.
-
B.
hasCrossStateStructure
Indicates that a structure spans or connects multiple states or state-level jurisdictions.
-
C.
hasCrossingPoint
Indicates that two or more entities intersect or share at least one common point in space or along their paths.
-
D.
hasCrossingLoops
Indicates that the related structure or path contains loops that intersect or cross over themselves.
-
E.
hadCrossingPoints
Indicates that two entities intersected or overlapped at one or more specific points in space or time.
- 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_69f76eb5e034819088e53ab5b7909a68 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fd5bf69acc819092a01e4259785dc3 |
completed | May 8, 2026, 3:43 a.m. |
| PD | Predicate disambiguation | batch_69fd59b3f4ac8190a7f9dd3142da6e09 |
completed | May 8, 2026, 3:34 a.m. |
Created at: May 3, 2026, 4:16 p.m.