Triple
T8070374
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Green Line E branch streetcar (surface portion) |
E188354
|
entity |
| Predicate | isPartiallyAtGrade |
P70125
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [Green Line E branch streetcar (surface portion), isPartiallyAtGrade, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isPartiallyAtGrade Context triple: [Green Line E branch streetcar (surface portion), isPartiallyAtGrade, true]
-
A.
isAtGrade
Indicates that an entity is positioned at or corresponds to a specific grade or level within an ordered scale or classification.
-
B.
isGradeWithin
Indicates that a given grade value falls within a specified acceptable or defined grade range.
-
C.
isPartially
chosen
Indicates that one entity is included within another to some extent, but not completely or fully.
-
D.
isElevatedOrAtGradeIn
Indicates that one entity is positioned either above ground level (elevated) or directly at ground level (at grade) within the context of another entity or environment.
-
E.
hasAtGradeStructure
Indicates that one entity includes or is associated with a structure located at ground level (at grade).
- 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_69ca82b42674819086840efea12478e5 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb3ffe29188190834ec4f71043a99d |
completed | March 31, 2026, 3:31 a.m. |
| PD | Predicate disambiguation | batch_69cb049cd51c8190bb3b0f503e42fa8d |
completed | March 30, 2026, 11:17 p.m. |
Created at: March 30, 2026, 5:27 p.m.