Triple
T7545548
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mattapan station |
E178391
|
entity |
| Predicate | hasLineCharacter |
P77918
|
FINISHED |
| Object | heritage streetcar-style light rail |
—
|
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: heritage streetcar-style light rail | Statement: [Mattapan station, hasLineCharacter, heritage streetcar-style light rail]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLineCharacter Context triple: [Mattapan station, hasLineCharacter, heritage streetcar-style light rail]
-
A.
hasLineLength
Indicates that one entity has, is characterized by, or is associated with a specific line length value.
-
B.
hasLineStructure
Indicates that one entity possesses or exhibits a linear arrangement or organization of its components.
-
C.
containsLine
Indicates that one entity includes or encloses a specific line within its spatial or structural extent.
-
D.
hasLineNumber
Indicates that something is associated with a specific line number, typically denoting its position within an ordered sequence such as lines of text or code.
-
E.
hasKeyLine
Indicates that one entity serves as the primary or central reference line for another entity, often used as a main axis or defining guideline.
- 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_69c69f2cbe08819088f9eb0c03ef529b |
completed | March 27, 2026, 3:15 p.m. |
| NER | Named-entity recognition | batch_69c6f898069881909fa8f9c885c4565b |
completed | March 27, 2026, 9:37 p.m. |
| PD | Predicate disambiguation | batch_69c6f4daad6c8190af2b8ae88d2c8cb7 |
completed | March 27, 2026, 9:21 p.m. |
| PDg | Predicate description generation | batch_69c6f8184bb08190b2f70545a6aa277c |
completed | March 27, 2026, 9:35 p.m. |
Created at: March 27, 2026, 3:48 p.m.