Triple
T8554132
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | R-net bus services |
E202520
|
entity |
| Predicate | operatedBy |
P86
|
FINISHED |
| Object | RET |
E153683
|
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: RET | Statement: [R-net bus services, operatedBy, RET]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: RET Context triple: [R-net bus services, operatedBy, RET]
-
A.
RET
chosen
RET is a public transport company operating buses, trams, and metro services in and around Rotterdam in the Netherlands.
-
B.
RE
RE is the common abbreviation for the British Army’s Corps of Royal Engineers, responsible for military engineering and technical support.
-
C.
RE
RE is a centrist, pro-European French political party founded by Emmanuel Macron and formerly known as La République En Marche!.
-
D.
RE
RE is the abbreviation for RegioExpress, a category of regional express trains commonly used in European rail transport.
-
E.
RE
RE is the two-letter ISO 3166-1 alpha-2 country code assigned to the French overseas department and region of Réunion.
- 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_69ca832610e08190b3b6c6cd2c250255 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe8894e7c8190bc0ae2ceec473ecb |
completed | March 31, 2026, 3:30 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ce6dd67d288190a147562a99ecde56 |
completed | April 2, 2026, 1:23 p.m. |
Created at: March 30, 2026, 6:19 p.m.