Triple
T36920853
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Pub Landlord |
E913192
|
entity |
| Predicate | spokenAccent |
P68361
|
FINISHED |
| Object | English accent |
—
|
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: English accent | Statement: [The Pub Landlord, spokenAccent, English accent]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: spokenAccent Context triple: [The Pub Landlord, spokenAccent, English accent]
-
A.
speaksWithAccentWhenUsing
chosen
Indicates that an entity consistently uses a particular accent when using a specified language, medium, or communication mode.
-
B.
voiceActorAccent
Indicates that a voice actor performs their role using a specified accent.
-
C.
spokenWord
Indicates that one entity has uttered or articulated a specific word or phrase in spoken form.
-
D.
speechAlsoKnownAs
Indicates that a speech or spoken work is referred to by an alternative name, title, or alias.
-
E.
correctPronunciation
Indicates that one entity provides the accurate or standard way to pronounce another entity (such as a word or name).
- 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_69f76e885b848190bad82c87e9525486 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69f9fdccda9881909409887cb8f533fb |
completed | May 5, 2026, 2:25 p.m. |
| PD | Predicate disambiguation | batch_69f7cf79ddb08190a083405cccc14137 |
completed | May 3, 2026, 10:43 p.m. |
Created at: May 3, 2026, 4:13 p.m.