Triple
T19295210
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maison à Bordeaux |
E482544
|
entity |
| Predicate | upperLevelCharacter |
P131606
|
FINISHED |
| Object | light and transparent |
—
|
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: light and transparent | Statement: [Maison à Bordeaux, upperLevelCharacter, light and transparent]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: upperLevelCharacter Context triple: [Maison à Bordeaux, upperLevelCharacter, light and transparent]
-
A.
upperLevels
Indicates that one entity occupies or corresponds to higher levels, tiers, or hierarchical positions relative to another entity.
-
B.
upperGrade
Indicates that one entity is in a higher grade level than another entity.
-
C.
upperStageRole
Indicates the functional role or purpose that a stage plays within the upper portion of a multi-stage system or structure.
-
D.
upperCourseOf
Indicates that one watercourse represents the upstream or higher-elevation segment of another watercourse within the same river system.
-
E.
hasUpperReachesCharacter
chosen
Indicates that an entity’s upper reaches or uppermost parts possess a particular characteristic or quality.
- 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_69d8e8cf61b0819096fe3e4107827c4e |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e5fc8533c08190822a917ffa32812d |
completed | April 20, 2026, 10:14 a.m. |
| PD | Predicate disambiguation | batch_69e4dd0bc7508190a6f9d56bd4c3404f |
completed | April 19, 2026, 1:47 p.m. |
Created at: April 10, 2026, 1:31 p.m.