Triple
T19639553
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Plzeň river system |
E471493
|
entity |
| Predicate | hasConfluenceIn |
P2416
|
FINISHED |
| Object | Plzeň city center |
—
|
LITERAL 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: Plzeň city center | Statement: [Plzeň river system, hasConfluenceIn, Plzeň city center]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasConfluenceIn Context triple: [Plzeň river system, hasConfluenceIn, Plzeň city center]
-
A.
hasMajorConfluence
Indicates that a watercourse joins with another watercourse at a significant or primary confluence point.
-
B.
confluenceWith
chosen
Indicates that one entity joins or merges together with another, typically at a shared meeting point.
-
C.
hasConcourse
Indicates that an entity includes, is connected to, or is served by a concourse area (such as a passageway or central hall).
-
D.
hasConcurrenceFrom
Indicates that an action, decision, or proposal is supported or agreed upon by another party or authority.
-
E.
startsAfterConfluenceOf
Indicates that one entity begins at a point located downstream from, and subsequent to, the confluence where two or more other entities merge.
- F. None of above.
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_69d8e511f28481909f4bc3ea9191e54a |
completed | April 10, 2026, 11:54 a.m. |
| NER | Named-entity recognition | batch_69e641215df48190926b38e6502bb83e |
completed | April 20, 2026, 3:07 p.m. |
| PD | Predicate disambiguation | batch_69e514e5cb108190ae260e466c447314 |
completed | April 19, 2026, 5:46 p.m. |
Created at: April 10, 2026, 1:44 p.m.