Triple
T4548359
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | RTS |
E110098
|
entity |
| Predicate | offersService |
P178
|
FINISHED |
| Object | RTS Un |
E110103
|
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: RTS Un | Statement: [RTS, offersService, RTS Un]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: RTS Un Context triple: [RTS, offersService, RTS Un]
-
A.
RTS
RTS is the Swiss public broadcasting organization that provides French-language radio, television, and digital media services.
-
B.
UNTS
UNTS is the official United Nations collection of treaties and international agreements registered or filed and recorded with the UN Secretariat.
-
C.
RTM
RTM is the commonly used abbreviation for Rosetta Terminology Mapping, a system for standardizing and aligning terminology across different datasets or domains.
-
D.
TRTS
TRTS is the commonly used abbreviation for the Taipei Metro rapid transit system serving the Taipei metropolitan area in Taiwan.
-
E.
RTS replay
chosen
RTS replay is the on-demand streaming platform of Switzerland’s public broadcaster Radio Télévision Suisse, offering catch-up access to its TV and radio programs.
- 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_69bd4412524c8190be5bcc9ddee91848 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd57f272248190983ae439bd0ac0cc |
completed | March 20, 2026, 2:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bdb945bd3881908e6c3f5f91b5f38e |
completed | March 20, 2026, 9:16 p.m. |
Created at: March 20, 2026, 1:05 p.m.