Triple
T159635
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Baltimore Light RailLink |
E3252
|
entity |
| Predicate | introducedBranding |
P1501
|
FINISHED |
| Object | 2015 (as Light RailLink) |
—
|
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: 2015 (as Light RailLink) | Statement: [Baltimore Light RailLink, introducedBranding, 2015 (as Light RailLink)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: introducedBranding Context triple: [Baltimore Light RailLink, introducedBranding, 2015 (as Light RailLink)]
-
A.
introduced
Indicates that one entity caused another entity to become known, presented, or brought into use for the first time to a person, group, or context.
-
B.
formerBrand
chosen
Indicates that an entity was previously used or recognized as a brand for another entity but is no longer its current brand.
-
C.
brand
Indicates that one entity is the commercial brand or label under which another entity (such as a product, service, or organization) is marketed or identified.
-
D.
introducedFor
Indicates that one entity was presented or brought to the attention of another entity for a specific purpose or role.
-
E.
introducedAfter
Indicates that one entity was introduced at a later time or stage than another entity.
- 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_69a2527757ec819090b8becb2cf1a862 |
completed | Feb. 28, 2026, 2:27 a.m. |
| NER | Named-entity recognition | batch_69a25855baf48190a1b63f2e5865d957 |
completed | Feb. 28, 2026, 2:52 a.m. |
| PD | Predicate disambiguation | batch_69a25660c2a48190b4174d5e6da3cb9d |
completed | Feb. 28, 2026, 2:43 a.m. |
Created at: Feb. 28, 2026, 2:31 a.m.