Triple
T26431095
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Place Ducale |
E664510
|
entity |
| Predicate | hasComparative |
P278
|
FINISHED |
| Object | often compared to Place des Vosges |
—
|
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: often compared to Place des Vosges | Statement: [Place Ducale, hasComparative, often compared to Place des Vosges]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasComparative Context triple: [Place Ducale, hasComparative, often compared to Place des Vosges]
-
A.
hasComparison
Indicates that one entity is being evaluated or contrasted relative to another entity based on some shared attribute or criterion.
-
B.
isComparedTo
chosen
Indicates that one entity is evaluated or measured in relation to another to highlight similarities, differences, or relative qualities.
-
C.
hasComparisonCriterion
Indicates that one entity is used as the basis or standard by which another entity is compared or evaluated.
-
D.
comparativeScale
Indicates a relationship where one entity is evaluated relative to another along a shared scale or dimension (such as size, intensity, or degree).
-
E.
enablesComparison
Indicates that one entity provides the means or conditions necessary to compare two or more entities with each other.
- 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_69ee883ad6a4819088f918e76122d690 |
completed | April 26, 2026, 9:48 p.m. |
| NER | Named-entity recognition | batch_69fda5003cdc8190a558501271389912 |
completed | May 8, 2026, 8:55 a.m. |
| PD | Predicate disambiguation | batch_69fda05bfc2c819096821a5300e9bb24 |
completed | May 8, 2026, 8:35 a.m. |
Created at: April 26, 2026, 11:49 p.m.