Triple
T13902938
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mancunian |
E334273
|
entity |
| Predicate | hasStereotypeOf |
P91566
|
FINISHED |
| Object | direct manner of speaking |
—
|
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: direct manner of speaking | Statement: [Mancunian, hasStereotypeOf, direct manner of speaking]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasStereotypeOf Context triple: [Mancunian, hasStereotypeOf, direct manner of speaking]
-
A.
hasStereotypeAssociation
chosen
Indicates that one entity is associated with another through a stereotype, implying a generalized or oversimplified characterization rather than an individually grounded attribute.
-
B.
hasStratotype
Indicates that one entity serves as the designated standard or reference example (stratotype) for defining the stratigraphic characteristics of another entity.
-
C.
hasArchetype
Indicates that one entity serves as the original model, pattern, or prototype upon which another entity is based or conceptually derived.
-
D.
hasStructureType
Indicates that an entity possesses or is classified by a specific structural type or configuration.
-
E.
hasContainmentType
Indicates the specific way in which one entity is contained within or enclosed by 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_69d81c5eaa9c819083b1ff8689179565 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de25db1e308190aaed6a21e443cc44 |
completed | April 14, 2026, 11:32 a.m. |
| PD | Predicate disambiguation | batch_69dd464b1ab48190ae50bfc902bf6ef7 |
completed | April 13, 2026, 7:38 p.m. |
Created at: April 9, 2026, 10:16 p.m.