Triple
T19385127
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | DLR Bank–Lewisham line |
E484913
|
entity |
| Predicate | usesRollingStock |
P5426
|
FINISHED |
| Object | DLR B90 stock |
—
|
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: DLR B90 stock | Statement: [DLR Bank–Lewisham line, usesRollingStock, DLR B90 stock]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: DLR B90 stock Context triple: [DLR Bank–Lewisham line, usesRollingStock, DLR B90 stock]
-
A.
B90 stock
chosen
B90 stock is a class of automated light rail vehicles used on London's Docklands Light Railway, introduced in the early 1990s to expand and modernize the system’s fleet.
-
B.
B94
B94 was a popular radio station brand used by WBZZ, known for its contemporary hit music format.
-
C.
B79
B79 is a designated route number for a major regional highway in New South Wales, Australia.
-
D.
B9
B9 is the fifth-generation Audi A4 platform, featuring updated styling, improved efficiency, and advanced technology over its predecessor.
-
E.
B99
B99 is a popular American comedy television series set in a Brooklyn police precinct, known for its ensemble cast, witty humor, and progressive themes.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e8d460d88190abf0591c5c9d2b0c |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e61b3ffa548190a060d6e94562a5d2 |
completed | April 20, 2026, 12:25 p.m. |
Created at: April 10, 2026, 1:35 p.m.