Triple
T19676328
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hôtel de Ville (Paris Métro) |
E472460
|
entity |
| Predicate | platformDecoration |
P60999
|
FINISHED |
| Object | white bevelled ceramic tiles |
—
|
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: white bevelled ceramic tiles | Statement: [Hôtel de Ville (Paris Métro), platformDecoration, white bevelled ceramic tiles]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: platformDecoration Context triple: [Hôtel de Ville (Paris Métro), platformDecoration, white bevelled ceramic tiles]
-
A.
platformAppearance
Indicates how an entity is visually presented or styled on a particular platform or interface.
-
B.
decorationSystem
Indicates a system or method used to apply, manage, or organize decorative elements in or around an entity.
-
C.
featuresDecor
Indicates that one entity includes or showcases the decor elements provided or defined by another entity.
-
D.
campaignDecoration
Indicates that something is used as a decorative element or embellishment within the context of a campaign.
-
E.
decorationForm
chosen
Indicates the specific decorative style, pattern, or motif that characterizes how something is ornamented.
- 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_69d8e514f2e08190ba70a4449519d218 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e641bbea8c8190b0ad841d95068e0e |
completed | April 20, 2026, 3:09 p.m. |
| PD | Predicate disambiguation | batch_69e514eb37b8819091502cc954f70eba |
completed | April 19, 2026, 5:46 p.m. |
Created at: April 10, 2026, 1:45 p.m.