Triple
T3620286
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cour d’honneur |
E76706
|
entity |
| Predicate | isFrontOf |
P4990
|
FINISHED |
| Object | main façade of the Élysée 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: main façade of the Élysée Palace | Statement: [Cour d’honneur, isFrontOf, main façade of the Élysée Palace]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isFrontOf Context triple: [Cour d’honneur, isFrontOf, main façade of the Élysée Palace]
-
A.
installedInFrontOf
Indicates that one object has been placed or mounted so that it is positioned directly in front of another object.
-
B.
hasFront
chosen
Indicates that an entity possesses or is associated with a front-facing side, surface, or portion.
-
C.
appearsBefore
Indicates that one entity occurs, is positioned, or is presented earlier in an ordered sequence than another entity.
-
D.
isInDirectionOf
Indicates that one entity is oriented or positioned toward the direction in which another entity lies.
-
E.
usedOnFront
Indicates that something is applied, displayed, or positioned on the front side or front-facing part of another object or 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_69ad85dae2fc81908d1ceadbc6af0089 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc2b85f6c819091000e231d9dac87 |
completed | March 8, 2026, 6:40 p.m. |
| PD | Predicate disambiguation | batch_69adb83f1e4c8190ab501c1c05b14c08 |
completed | March 8, 2026, 5:56 p.m. |
Created at: March 8, 2026, 3:23 p.m.