Triple
T25455256
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Corps des Pages |
E637896
|
entity |
| Predicate | uniformSimilarTo |
P94757
|
FINISHED |
| Object | uniform of the Imperial Guard |
—
|
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: uniform of the Imperial Guard | Statement: [Corps des Pages, uniformSimilarTo, uniform of the Imperial Guard]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: uniformSimilarTo Context triple: [Corps des Pages, uniformSimilarTo, uniform of the Imperial Guard]
-
A.
lessSimilarTo
Indicates that one entity is considered to share fewer similarities or a weaker resemblance with another entity compared to some reference or alternative.
-
B.
materiallySimilarTo
Indicates that two entities share substantially the same physical or material characteristics, composition, or properties, though they may not be exactly identical.
-
C.
hasSimilarityTo
chosen
Indicates that one entity shares common characteristics, features, or qualities with another entity to a notable degree.
-
D.
areUniform
Indicates that all elements in a given set or collection share the same value, property, or characteristic.
-
E.
resembles
Indicates that one entity is similar in appearance, form, or characteristics to another.
- 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_69e75db7c5048190b8da9cd7eeedb610 |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f5f725e4d08190b0304e45a417193b |
completed | May 2, 2026, 1:07 p.m. |
| PD | Predicate disambiguation | batch_69f4683b34748190818428489a226124 |
completed | May 1, 2026, 8:45 a.m. |
Created at: April 21, 2026, 2:04 p.m.