Triple
T18410088
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Louvre Pyramid courtyard |
E441732
|
entity |
| Predicate | roleInUrbanAxis |
P8652
|
FINISHED |
| Object | node on the Paris historical axis |
—
|
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: node on the Paris historical axis | Statement: [Louvre Pyramid courtyard, roleInUrbanAxis, node on the Paris historical axis]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleInUrbanAxis Context triple: [Louvre Pyramid courtyard, roleInUrbanAxis, node on the Paris historical axis]
-
A.
hasUrbanRole
Indicates that an entity plays a specific functional or social role within an urban or city context.
-
B.
roleInUrbanPlan
Indicates the specific function, responsibility, or position an entity holds within an urban planning context or scheme.
-
C.
urbanRole
chosen
Indicates the function, status, or role that an entity holds within an urban or city context.
-
D.
refersToUrbanFeature
Indicates that one entity makes reference or points specifically to an urban feature such as a city-related structure, space, or infrastructure element.
-
E.
focusCityRole
Indicates that a city serves a particular primary role or function within a broader geographic or organizational context.
- 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_69d8b9eb8a508190a942fd75ebd8b1dc |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e5195b98808190b9cfb2e444f2b524 |
completed | April 19, 2026, 6:05 p.m. |
| PD | Predicate disambiguation | batch_69e469bf7f74819096a01173493412c2 |
completed | April 19, 2026, 5:35 a.m. |
Created at: April 10, 2026, 10:47 a.m.