Triple
T15531418
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | École Militaire |
E370225
|
entity |
| Predicate | hasCanopyAtEntrance |
P12642
|
FINISHED |
| Object | Guimard-style entrance canopy (one entrance) |
—
|
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: Guimard-style entrance canopy (one entrance) | Statement: [École Militaire, hasCanopyAtEntrance, Guimard-style entrance canopy (one entrance)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCanopyAtEntrance Context triple: [École Militaire, hasCanopyAtEntrance, Guimard-style entrance canopy (one entrance)]
-
A.
hasCanopy
Indicates that one entity possesses or is characterized by a canopy associated with it.
-
B.
hasCanopyDensity
Indicates the degree to which a canopy (such as a tree or forest cover) occupies or obscures the area beneath it.
-
C.
hasEntranceStructure
chosen
Indicates that one entity possesses or is associated with a specific physical structure that serves as its entrance.
-
D.
hasEntrance
Indicates that one entity possesses or provides an entry point or access way to another entity or space.
-
E.
hasEntranceOn
Indicates that one entity’s entrance or access point is located on or faces a specified side, boundary, or feature of another entity.
- 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_69d85cc521a08190921fb50319dddc34 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e0414773548190b3311515f9d957dd |
completed | April 16, 2026, 1:54 a.m. |
| PD | Predicate disambiguation | batch_69deda7a95c48190bbe29fadcf17191a |
completed | April 15, 2026, 12:23 a.m. |
Created at: April 10, 2026, 4:06 a.m.