Triple
T3917089
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | LMS Black Five |
E88866
|
entity |
| Predicate | notableExample |
P1503
|
FINISHED |
| Object | LMS 45110 |
E88866
|
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: LMS 45110 | Statement: [LMS Black Five, notableExample, LMS 45110]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: LMS 45110 Context triple: [LMS Black Five, notableExample, LMS 45110]
-
A.
LMS 8F
LMS 8F is a class of British heavy freight steam locomotives widely used during and after World War II for hauling goods trains.
-
B.
LMS
LMS was one of the "Big Four" British railway companies, operating an extensive network across London, the Midlands, Scotland, and parts of Wales from 1923 until nationalisation in 1948.
-
C.
LMS
LMS is the London Mathematical Society, a leading UK organization dedicated to advancing and promoting mathematical research.
-
D.
LMS Black Five
chosen
LMS Black Five is a highly successful and versatile class of British mixed-traffic steam locomotives designed by William Stanier for widespread use across the LMS network.
-
E.
L110
L110 is the liquid-fueled second stage used on ISRO’s GSLV Mk III heavy-lift launch vehicle.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69aed955229881909e85e73ffab1d343 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aeed5797508190adaddb84575d9bb3 |
completed | March 9, 2026, 3:55 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b52864e0488190ab348a52cb9168b9 |
completed | March 14, 2026, 9:20 a.m. |
Created at: March 9, 2026, 3:22 p.m.