Triple
T28021042
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Crosstown Local |
E707687
|
entity |
| Predicate | connectsWithoutEntering |
P192757
|
FINISHED |
| Object | Manhattan |
—
|
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: Manhattan | Statement: [Crosstown Local, connectsWithoutEntering, Manhattan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: connectsWithoutEntering Context triple: [Crosstown Local, connectsWithoutEntering, Manhattan]
-
A.
notConnectedBy
Indicates that there is no direct link, path, or relationship connecting the referenced entities.
-
B.
connectsWithin
Indicates that one entity establishes a connection or link between elements that lie inside the bounds or scope of another entity.
-
C.
connectionTo
Indicates a relationship in which one entity is linked, associated, or otherwise related to another entity.
-
D.
enterAs
Indicates that one entity goes into or joins another context, place, or role in the capacity or form specified.
-
E.
connectionStandard
Indicates the technical standard or protocol that defines how a connection between entities is established and operates.
- 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_69ef96baf3a881909a2b63844185dddd |
completed | April 27, 2026, 5:02 p.m. |
| NER | Named-entity recognition | batch_69fd2a215d6c8190a1a428ccaee603f1 |
completed | May 8, 2026, 12:11 a.m. |
| PD | Predicate disambiguation | batch_69fd28ef19688190bb8370f2812a43e7 |
completed | May 8, 2026, 12:06 a.m. |
| PDg | Predicate description generation | batch_69fd2a2095f88190bfcbcb2973516ffc |
completed | May 8, 2026, 12:11 a.m. |
Created at: April 27, 2026, 8:10 p.m.