Triple
T9810781
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New Haven Line at Grand Central Terminal |
E238263
|
entity |
| Predicate | startingPointDirection |
P40031
|
FINISHED |
| Object | northeast |
—
|
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: northeast | Statement: [New Haven Line at Grand Central Terminal, startingPointDirection, northeast]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: startingPointDirection Context triple: [New Haven Line at Grand Central Terminal, startingPointDirection, northeast]
-
A.
startPoint
Indicates the initial location or position from which an object, path, or action begins.
-
B.
approachDirection
Indicates the direction or bearing from which one entity moves closer to or advances toward another entity.
-
C.
startingForwardEast
Indicates that an entity begins its movement or orientation facing toward the east direction.
-
D.
directionRelativeTo
Indicates the spatial orientation of one entity in relation to another, such as which way it faces or points relative to a reference entity.
-
E.
approximateDirection
chosen
Indicates that one entity is located in a general or rough directional relation (e.g., roughly north, south, etc.) relative to another entity, without specifying an exact bearing.
- 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_69ca84defac48190abc1148804f184c1 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdb2214a7c8190b516acf64e2b85db |
completed | April 2, 2026, 12:02 a.m. |
| PD | Predicate disambiguation | batch_69cd03dd2da881909052fbf29736a773 |
completed | April 1, 2026, 11:39 a.m. |
Created at: March 30, 2026, 8:30 p.m.