Triple
T9293929
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cheonan |
E223590
|
entity |
| Predicate | servedByHighSpeedRail |
P48478
|
FINISHED |
| Object | SRT |
E610745
|
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: SRT | Statement: [Cheonan, servedByHighSpeedRail, SRT]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: SRT Context triple: [Cheonan, servedByHighSpeedRail, SRT]
-
A.
SRT
SRT was the former name of Toronto’s Line 3 Scarborough, an elevated light rapid transit line that operated in the city’s eastern suburbs.
-
B.
SRT
chosen
SRT is a South Korean high-speed rail service that operates on major routes including those connecting through Daejeon.
-
C.
SRT
SRT is a high-performance trim level of Jeep vehicles, featuring upgraded powertrains, sport-tuned components, and enhanced styling.
-
D.
RTM
RTM is the commonly used abbreviation for Rosetta Terminology Mapping, a system for standardizing and aligning terminology across different datasets or domains.
-
E.
RTM
RTM is the IATA airport code for Rotterdam The Hague Airport, a regional international airport serving the Rotterdam–The Hague metropolitan area in the Netherlands.
- 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_69ca8423edb08190bc0c91287a484768 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd089a2ed0819086b2e4219ff2453e |
completed | April 1, 2026, 11:59 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d0b241251c81909aa4e8bcf5cd9c2e |
completed | April 4, 2026, 6:40 a.m. |
Created at: March 30, 2026, 7:35 p.m.