Triple
T13070358
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rokin metro station |
E329438
|
entity |
| Predicate | serves |
P98
|
FINISHED |
| Object | Rokin |
E65569
|
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: Rokin | Statement: [Rokin metro station, serves, Rokin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rokin Context triple: [Rokin metro station, serves, Rokin]
-
A.
Rokin
chosen
Rokin is a major street and canal in central Amsterdam, known for its historic buildings, shops, and proximity to Dam Square.
-
B.
Rairok
Rairok is a small islet and community area within the Marshall Islands' capital atoll of Majuro.
-
C.
Rohin
Rohin is a central fictional protagonist characterized by an alluring, confident persona.
-
D.
Roden
Roden is a town in the Dutch province of Drenthe known as a local service and population center within the municipality of Noordenveld.
-
E.
Roden
Roden is a Czech surname most notably borne by actor Karel Roden, known for his work in both Czech and international films.
- 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_69d80771749c81909a6d9197b9504872 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69d980ee6130819095d835e7ff6a8c5b |
completed | April 10, 2026, 10:59 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6d60510dc81909e0cba8b63a50d9c |
completed | May 3, 2026, 4:58 a.m. |
Created at: April 9, 2026, 9 p.m.