Triple
T36531257
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kearny Connection |
E900448
|
entity |
| Predicate | associatedServiceName |
P24023
|
FINISHED |
| Object | Midtown Direct |
E2187217
|
NE 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: Midtown Direct | Statement: [Kearny Connection, associatedServiceName, Midtown Direct]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedServiceName Context triple: [Kearny Connection, associatedServiceName, Midtown Direct]
-
A.
linkedByServiceTo
Indicates that one entity is connected or associated with another through a specific service acting as the linking mechanism.
-
B.
relatedService
Indicates that one service is connected or associated with another service in a relevant or dependent way.
-
C.
associatedName
chosen
Indicates that one entity has an alternative or related name that is linked or connected to another entity.
-
D.
associatedSystem
Indicates that one entity is functionally or contextually linked to a particular system with which it interacts or to which it belongs.
-
E.
relatedApplication
Indicates that one application has a defined connection or association with another application, such as dependency, complementarity, or functional linkage.
- F. None of above.
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_69f76e5fbb388190b70c4c15573c8143 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a037c8e2c648190a65fc9c7872861af |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a39e6dcddac8190bdd6afc0f9f503d3 |
completed | June 23, 2026, 1:52 a.m. |
| PD | Predicate disambiguation | batch_6a037a0bf4b88190bdcfae9a14b51f0a |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:11 p.m.