Triple
T21907467
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brighella |
E540975
|
entity |
| Predicate | relationshipToHarlequin |
P34570
|
FINISHED |
| Object | more calculating than Harlequin |
—
|
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: more calculating than Harlequin | Statement: [Brighella, relationshipToHarlequin, more calculating than Harlequin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipToHarlequin Context triple: [Brighella, relationshipToHarlequin, more calculating than Harlequin]
-
A.
literaryRelationship
Indicates a relationship between entities that are connected through literature, such as authorship, influence, adaptation, or other text-based associations.
-
B.
relationshipToBooks
Indicates the nature or type of connection an entity has with one or more books, such as ownership, authorship, usage, or preference.
-
C.
fictionalRelationship
chosen
Indicates a relationship that exists only within a fictional or imagined context between entities.
-
D.
relationshipToLady
Indicates the specific type of social, familial, or personal connection that one entity has to a lady.
-
E.
hasAuthorRelationship
Indicates a relationship where one entity serves as the author or creator of another entity (such as a work, document, or resource).
- 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_69e0c47b4e8c81908c8076eaa4c8e4f2 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f121d806688190b23502aacbfde4bd |
completed | April 28, 2026, 9:08 p.m. |
| PD | Predicate disambiguation | batch_69e6be9ebf4c8190892df1a8e1313f88 |
completed | April 21, 2026, 12:02 a.m. |
Created at: April 16, 2026, 7:38 p.m.