Triple
T7233363
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | San Lázaro metro station |
E154956
|
entity |
| Predicate | hasPictogram |
P37076
|
FINISHED |
| Object | stylized image of the Legislative Palace |
—
|
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: stylized image of the Legislative Palace | Statement: [San Lázaro metro station, hasPictogram, stylized image of the Legislative Palace]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPictogram Context triple: [San Lázaro metro station, hasPictogram, stylized image of the Legislative Palace]
-
A.
hasIconographicFigure
chosen
Indicates that one entity includes, depicts, or is associated with a particular iconographic figure in its visual or symbolic representation.
-
B.
hasApproximateNumberOfPictographs
Indicates that an entity is associated with a quantity of pictographs that is not exact but estimated or approximate.
-
C.
hasIllustrationsBy
Indicates that one entity (such as a work or publication) includes illustrations that were created by another entity (the illustrator).
-
D.
containsImage
Indicates that one entity includes or embeds an image as part of its content or structure.
-
E.
hasIllustrations
Indicates that an entity includes or is accompanied by visual illustrations.
- 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_69c68811dd1c8190ac460bb39e64e1f0 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6ea552a688190a00f5d0ad982f787 |
completed | March 27, 2026, 8:36 p.m. |
| PD | Predicate disambiguation | batch_69c6e7644648819096a5e2de5d0dbe97 |
completed | March 27, 2026, 8:24 p.m. |
Created at: March 27, 2026, 2:55 p.m.