Triple
T21299976
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gorzów Wielkopolski |
E525032
|
entity |
| Predicate | river |
P165
|
FINISHED |
| Object | Warta |
E310280
|
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: Warta | Statement: [Gorzów Wielkopolski, river, Warta]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Warta Context triple: [Gorzów Wielkopolski, river, Warta]
-
A.
Warta
chosen
Warta is a major river in western-central Poland that flows through several important cities before joining the Oder River.
-
B.
Warta
Warta is a small historic town in central Poland, situated in the Sieradz region along the Warta River.
-
C.
Patrika
Patrika is a traditional village on the Greek island of Chios, known for its role within the historic mastic-producing region of Mastichochoria.
-
D.
Kourier
Kourier is a lightweight, Knative-focused ingress and networking layer designed to efficiently route and manage traffic for serverless workloads on Kubernetes.
-
E.
Habero
Habero is a town located in Eritrea's Anseba region, known primarily as a small agricultural and pastoral community.
- 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_69e0b517e6748190850d6f6ddf323d69 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e7385b1c548190b940ded0163ee3ca |
completed | April 21, 2026, 8:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a099814529c8190a94cfd3355862d0f |
completed | May 17, 2026, 10:27 a.m. |
Created at: April 16, 2026, 4:05 p.m.