Triple
T8142808
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Balcony (figure in Manet’s painting) |
E190136
|
entity |
| Predicate | hasPropNearby |
P18252
|
FINISHED |
| Object | green balcony railing |
—
|
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: green balcony railing | Statement: [The Balcony (figure in Manet’s painting), hasPropNearby, green balcony railing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPropNearby Context triple: [The Balcony (figure in Manet’s painting), hasPropNearby, green balcony railing]
-
A.
hasNearbyFunction
Indicates that one entity has another entity located close by that serves a related or supportive function.
-
B.
hasNearbyMode
chosen
Indicates that one entity has another entity located close enough to be considered in its immediate vicinity or surrounding area.
-
C.
hasNotableNearbyEntity
Indicates that one entity has another significant or noteworthy entity located in its close physical or contextual proximity.
-
D.
hasOpenSpaceNearby
Indicates that an entity is located near or adjacent to an area that is open, unobstructed, or undeveloped.
-
E.
hasNearbySquare
Indicates that one entity has at least one square-shaped entity located close to it in space.
- 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_69ca82bd9900819099477cdc2eb4244f |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb4443a3748190bbae79f1d673c03d |
completed | March 31, 2026, 3:49 a.m. |
| PD | Predicate disambiguation | batch_69cb369c0d0481908762c488d7f77e74 |
completed | March 31, 2026, 2:51 a.m. |
Created at: March 30, 2026, 5:36 p.m.