Triple
T2514152
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Birkirkara |
E52770
|
entity |
| Predicate | hasTwinTown |
P919
|
FINISHED |
| Object | Tivoli |
E88741
|
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: Tivoli | Statement: [Birkirkara, hasTwinTown, Tivoli]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tivoli Context triple: [Birkirkara, hasTwinTown, Tivoli]
-
A.
Tivoli
chosen
Tivoli is an Italian hill town east of Rome renowned for its historic villas and gardens, including Emperor Hadrian’s vast imperial retreat, Hadrian’s Villa.
-
B.
Tivoli
Tivoli is an IBM software brand known for its enterprise systems management and monitoring solutions.
-
C.
TivoliVredenburg
TivoliVredenburg is a large, modern music complex and cultural venue in Utrecht, Netherlands, known for its multiple concert halls and diverse live performances.
-
D.
Schmidt Tivoli
Schmidt Tivoli is a well-known theater and cabaret venue in Hamburg, Germany, famed for its variety shows and musical productions.
-
E.
Belvedere
Belvedere is an affluent, scenic waterfront city in Marin County, California, known for its views of San Francisco Bay and upscale residential character.
- 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_69ab4958e76481908a235377dd921c9e |
completed | March 6, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69abd20c8ab0819096d6a654039beb39 |
completed | March 7, 2026, 7:21 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69af2b934d3c81909627a5f4d6e6ca6a |
completed | March 9, 2026, 8:20 p.m. |
Created at: March 6, 2026, 9:46 p.m.