Triple
T9210138
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Leiderdorp |
E221090
|
entity |
| Predicate | hasWaterway |
P5565
|
FINISHED |
| Object | Zijl |
E610180
|
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: Zijl | Statement: [Leiderdorp, hasWaterway, Zijl]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Zijl Context triple: [Leiderdorp, hasWaterway, Zijl]
-
A.
Zijl
chosen
Zijl is a waterway in the Dutch province of South Holland that serves as an important connection between local lakes and canals in the Leiden region.
-
B.
Eendracht
Eendracht was a prominent 17th-century Dutch warship that served as the flagship of the Dutch fleet during major naval engagements of the Anglo-Dutch Wars.
-
C.
Eendracht
Eendracht is a waterway in the southwestern Netherlands that forms part of the main shipping route between the Scheldt and Rhine river systems.
-
D.
Zijdelwaard
Zijdelwaard is a residential neighborhood in the town of Uithoorn in the province of North Holland, Netherlands.
-
E.
De Blaa
De Blaa is the commonly used nickname for the Norwegian football club Stabæk Fotball, referring to the team's traditional blue colors.
- 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_69ca83e9d0e081908bdb71097201a06c |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69ccd9b54520819087030148dadd6385 |
completed | April 1, 2026, 8:39 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d065efcb64819097d4624bd9e423d2 |
completed | April 4, 2026, 1:14 a.m. |
Created at: March 30, 2026, 7:26 p.m.