Triple
T35458529
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Beltway 8 |
E1024846
|
entity |
| Predicate | outerLoopRelativeTo |
P183312
|
FINISHED |
| Object | Interstate 610 |
—
|
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: Interstate 610 | Statement: [Beltway 8, outerLoopRelativeTo, Interstate 610]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: outerLoopRelativeTo Context triple: [Beltway 8, outerLoopRelativeTo, Interstate 610]
-
A.
directionRelativeToOuterLoop
Indicates the orientation or turning direction of an element relative to the path or traversal direction of an enclosing outer loop.
-
B.
relativePosition
Indicates the spatial relationship of one entity’s location with respect to another entity’s position.
-
C.
operatesRelativeTo
Indicates that one entity performs its function or behavior in reference to, or as a function of, another entity’s state, position, or parameters.
-
D.
relativePositioning
Indicates how one entity is spatially arranged or located in relation to another entity.
-
E.
positionedRelativeTo
Indicates that one entity’s spatial location is defined or described in relation to the position of another entity.
- F. None of above. chosen
Provenance (4 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_69f76df92f108190817222e520e22268 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f79da9f80c8190b0afd8509f28747b |
completed | May 3, 2026, 7:10 p.m. |
| PD | Predicate disambiguation | batch_69f79617d40481909ba372f94209c08b |
completed | May 3, 2026, 6:38 p.m. |
| PDg | Predicate description generation | batch_69f79da8d8848190ab5ab1bdad95d58c |
completed | May 3, 2026, 7:10 p.m. |
Created at: May 3, 2026, 4:04 p.m.