Triple
T7008686
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frankston line |
E162523
|
entity |
| Predicate | rollingStock |
P1305
|
FINISHED |
| Object | Comeng train |
E606704
|
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: Comeng train | Statement: [Frankston line, rollingStock, Comeng train]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Comeng train Context triple: [Frankston line, rollingStock, Comeng train]
-
A.
Comeng EMU
chosen
The Comeng EMU is a long-serving class of electric multiple unit trains used on Melbourne's suburban rail network.
-
B.
Civia EMU
Civia EMU is a class of electric multiple unit commuter trains used by Spain’s Renfe for suburban and regional passenger services.
-
C.
XPT train
The XPT train is a long-distance, high-speed diesel passenger train used in New South Wales, Australia, based on the British InterCity 125 design.
-
D.
Hitachi A-Train
The Hitachi A-Train is a modular family of lightweight, aluminum-bodied electric and diesel-electric multiple units designed by Hitachi for high-speed and commuter rail services worldwide.
-
E.
MX3000 train
The MX3000 train is a modern electric multiple unit used as the primary passenger rolling stock on the Oslo Metro system in Norway.
- 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_69c6885928148190ae31909fbb5e9849 |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6dc36e3fc8190957445132a9ffb5f |
completed | March 27, 2026, 7:36 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c775612fe88190822f297f2bec6cd1 |
completed | March 28, 2026, 6:29 a.m. |
Created at: March 27, 2026, 2:33 p.m.