Triple
T26159714
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Delancey Street (BMT Nassau Street Line) |
E660072
|
entity |
| Predicate | servesLocale |
P180115
|
FINISHED |
| Object | Lower East Side |
E151862
|
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: Lower East Side | Statement: [Delancey Street (BMT Nassau Street Line), servesLocale, Lower East Side]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: servesLocale Context triple: [Delancey Street (BMT Nassau Street Line), servesLocale, Lower East Side]
-
A.
locale
Indicates that one entity is the place, setting, or geographic area in which another entity exists, occurs, or is situated.
-
B.
currentLanguageOfServices
Indicates that a specified language is the one presently used to provide or deliver certain services.
-
C.
localeType
Indicates the classification or category of a locale (such as region, city, or venue type) that characterizes the kind of place involved in the relationship.
-
D.
hasLocalServicesLanguage
Indicates that the local services available in a given context operate or are provided using a specified language.
-
E.
localizationBy
Indicates a relationship where one entity determines, specifies, or constrains the spatial or contextual location of another entity.
- F. None of above. chosen
Provenance (5 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_69ee5bc5a9908190899d39ce95c6d215 |
completed | April 26, 2026, 6:39 p.m. |
| NER | Named-entity recognition | batch_69f73223675481908c1bc3208c0f5284 |
completed | May 3, 2026, 11:31 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a118f9acfdc81909175a321137a94d4 |
completed | May 23, 2026, 11:29 a.m. |
| PD | Predicate disambiguation | batch_69f7317690108190b3aae2cd2e1d069e |
completed | May 3, 2026, 11:28 a.m. |
| PDg | Predicate description generation | batch_69f73221eef88190bd8905e6e9f5a586 |
completed | May 3, 2026, 11:31 a.m. |
Created at: April 26, 2026, 8:29 p.m.