Triple
T611655
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Élysée Palace |
E12111
|
entity |
| Predicate | hasGardenArea |
P12538
|
FINISHED |
| Object | large private park in central Paris |
—
|
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: large private park in central Paris | Statement: [Élysée Palace, hasGardenArea, large private park in central Paris]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasGardenArea Context triple: [Élysée Palace, hasGardenArea, large private park in central Paris]
-
A.
hasGardenType
chosen
Indicates that an entity possesses or is associated with a garden of a specified type.
-
B.
hasCourtyard
Indicates that one entity includes, features, or is characterized by the presence of a courtyard.
-
C.
hasLandscaping
Indicates that an entity possesses or is associated with designed outdoor grounds or landscape features.
-
D.
hasIrrigationArea
Indicates that an entity possesses or is associated with a specific area of land equipped or designated for irrigation.
-
E.
hasResidentialArea
Indicates that an entity includes, contains, or is associated with an area designated for people to live or reside.
- 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_69a493309df48190a327f748e88049a6 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a49e07739481909930a6577c081b9e |
completed | March 1, 2026, 8:13 p.m. |
| PD | Predicate disambiguation | batch_69a49cfa7b4481909bec7a5fd3e98c65 |
completed | March 1, 2026, 8:09 p.m. |
Created at: March 1, 2026, 7:35 p.m.