Triple
T36679584
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vesdre valley |
E905640
|
entity |
| Predicate | upstreamTown |
P63897
|
FINISHED |
| Object | Eupen |
—
|
NE NERFINISHED |
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: Eupen | Statement: [Vesdre valley, upstreamTown, Eupen]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: upstreamTown Context triple: [Vesdre valley, upstreamTown, Eupen]
-
A.
upstreamCity
Indicates that one city is located upstream along a river or waterway relative to another city.
-
B.
upstreamRiver
Indicates that one river is located or flows in an upstream direction relative to another river within the same watercourse system.
-
C.
upstreamDam
Indicates that one entity is located or positioned upstream of another entity in relation to a dam, typically affecting or influenced by the dam’s presence or operation.
-
D.
upstream
Indicates that one entity is located or occurs in the direction from which a flow (such as water, data, or process sequence) originates relative to another entity.
-
E.
situatedUpstreamOf
chosen
Indicates that one entity is located in the direction from which a flow (such as water, traffic, or a process stream) originates relative to another entity along the same path or system.
- 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_69f76e7011dc819082b324f18b756a1b |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69f7c7be0be88190a480393a2d1ee5bf |
completed | May 3, 2026, 10:10 p.m. |
| PD | Predicate disambiguation | batch_69f7c4796ebc819084a0dc08505e5f14 |
completed | May 3, 2026, 9:56 p.m. |
Created at: May 3, 2026, 4:12 p.m.