Triple
T35887386
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Senne valley |
E1037686
|
entity |
| Predicate | partlyLocatedUnder |
P15446
|
FINISHED |
| Object | Brussels city center (covered Senne section) |
—
|
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: Brussels city center (covered Senne section) | Statement: [Senne valley, partlyLocatedUnder, Brussels city center (covered Senne section)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: partlyLocatedUnder Context triple: [Senne valley, partlyLocatedUnder, Brussels city center (covered Senne section)]
-
A.
partlyLocatedNear
Indicates that one entity is situated near another, but only a portion or subset of it lies within that nearby area.
-
B.
partlyLocatedOn
chosen
Indicates that one entity is situated such that only a portion of it lies on or within the spatial extent of another entity.
-
C.
partiallyOn
Indicates that one entity rests or extends over another such that only a portion of its area, volume, or length is supported or in contact.
-
D.
partlyCoveredBy
Indicates that one entity is covered or overlapped by another entity, but only to a partial extent rather than completely.
-
E.
partiallyEnclosed
Indicates that one entity surrounds or covers another entity to some extent, but not completely.
- 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_69f76e1f4d748190bb55594d8441d70e |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7aa3883d48190b05e3d2da7a017ae |
completed | May 3, 2026, 8:04 p.m. |
| PD | Predicate disambiguation | batch_69f7a8d435288190b30b1991fb003121 |
completed | May 3, 2026, 7:58 p.m. |
Created at: May 3, 2026, 4:06 p.m.