Triple
T8070382
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Green Line E branch streetcar (surface portion) |
E188354
|
entity |
| Predicate | branchLetter |
P57950
|
FINISHED |
| Object | E |
—
|
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: E | Statement: [Green Line E branch streetcar (surface portion), branchLetter, E]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: branchLetter Context triple: [Green Line E branch streetcar (surface portion), branchLetter, E]
-
A.
branchPosition
Indicates the relative location or placement of something along a branch.
-
B.
branchesFrom
Indicates that one entity originates or diverges from another as a subordinate or offshoot path, structure, or lineage.
-
C.
branchPoint
Indicates a point in a process, structure, or path where a single preceding element splits into two or more alternative continuations or options.
-
D.
branchLabel
chosen
Indicates the label or name assigned to a specific branch within a hierarchical or branching structure.
-
E.
branchComposition
Indicates that one branch or subdivision is structurally or functionally composed of, or made up from, another entity or set of entities.
- 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.