Triple
T24739998
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Murray Avenue |
E618526
|
entity |
| Predicate | parallelOrConnectedTo |
P91241
|
FINISHED |
| Object | Forbes Avenue (Squirrel Hill business district) |
—
|
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: Forbes Avenue (Squirrel Hill business district) | Statement: [Murray Avenue, parallelOrConnectedTo, Forbes Avenue (Squirrel Hill business district)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: parallelOrConnectedTo Context triple: [Murray Avenue, parallelOrConnectedTo, Forbes Avenue (Squirrel Hill business district)]
-
A.
partlyConnectedBy
Indicates that two entities are linked or joined by something in an incomplete, partial, or not fully continuous way.
-
B.
connectedByStraitTo
Indicates that one entity is geographically linked to another by a narrow body of water known as a strait.
-
C.
organizedInParallelWith
Indicates that one process, event, or activity is arranged or carried out at the same time and in coordination with another, rather than sequentially.
-
D.
connectsTo
Indicates a relationship where one entity is linked or joined to another, allowing interaction, communication, or transfer between them.
-
E.
parallel
chosen
Indicates that two or more entities maintain a constant separation and direction without intersecting or converging.
- 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_69e2fab8f95c81908bb9e552cf3280c2 |
completed | April 18, 2026, 3:30 a.m. |
| NER | Named-entity recognition | batch_69f410a25ab88190a72db43043c1f6ff |
completed | May 1, 2026, 2:32 a.m. |
| PD | Predicate disambiguation | batch_69f40ef612c88190ab2f3f08d4a92018 |
completed | May 1, 2026, 2:24 a.m. |
Created at: April 18, 2026, 4:04 a.m.