Triple
T16728493
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Runda |
E406524
|
entity |
| Predicate | nearbyPlace |
P2064
|
FINISHED |
| Object | Ruaka |
E1042477
|
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: Ruaka | Statement: [Runda, nearbyPlace, Ruaka]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ruaka Context triple: [Runda, nearbyPlace, Ruaka]
-
A.
Ruaka
chosen
Ruaka is a rapidly growing residential and commercial suburb on the outskirts of Nairobi, Kenya, known for its proximity to upscale neighborhoods and major shopping centers.
-
B.
Raki
Raki is a traditional Turkish anise-flavored alcoholic spirit, often enjoyed diluted with water alongside meze.
-
C.
Maloja
Maloja is a small Swiss mountain village and pass in the Upper Engadine region of the canton of Graubünden, known for its scenic alpine landscapes and access to nearby lakes and hiking trails.
-
D.
Rolava
Rolava is a river in the Czech Republic that flows through the Ore Mountains region before joining the Ohře River.
-
E.
Rokava
Rokava is a small river in southwestern Slovenia that serves as a tributary of the Dragonja River in the Istrian region.
- 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_69d8838f242881908abd8bc138795886 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e38749baa48190892b2e2b978f6eb6 |
completed | April 18, 2026, 1:29 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a009d483a8c8190b127f32dcc21be5a |
completed | May 10, 2026, 2:59 p.m. |
Created at: April 10, 2026, 5:20 a.m.