Triple
T20270628
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Belgian Shepherd Dog |
E499081
|
entity |
| Predicate | commonRole |
P18942
|
FINISHED |
| Object | K9 police dog |
—
|
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: K9 police dog | Statement: [Belgian Shepherd Dog, commonRole, K9 police dog]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: commonRole Context triple: [Belgian Shepherd Dog, commonRole, K9 police dog]
-
A.
typicalRole
chosen
Indicates that one entity serves as the usual, characteristic, or commonly expected role or function of another entity.
-
B.
possibleRole
Indicates that an entity is capable of or eligible to serve in a particular role or function in a given context.
-
C.
typicalAdditionalRole
Indicates that an entity commonly or characteristically holds an extra role or function in addition to its primary one.
-
D.
canonicalRole
Indicates that an entity holds a standard, primary, or officially recognized role within a particular context or system.
-
E.
roleInText
Indicates that an entity participates in a text with a specific function or capacity (e.g., author, editor, character).
- 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_69da6275fa6c8190952924930adee150 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e675dd7c58819095bbf4baeda04d6a |
completed | April 20, 2026, 6:52 p.m. |
| PD | Predicate disambiguation | batch_69e55b1e5e1c8190ba8a5544b1db9e1d |
completed | April 19, 2026, 10:45 p.m. |
Created at: April 11, 2026, 11:42 p.m.