Triple
T31253075
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thomas Wake |
E796882
|
entity |
| Predicate | hasSpeakingStyle |
P192376
|
FINISHED |
| Object | old-fashioned sailor dialect |
—
|
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: old-fashioned sailor dialect | Statement: [Thomas Wake, hasSpeakingStyle, old-fashioned sailor dialect]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSpeakingStyle Context triple: [Thomas Wake, hasSpeakingStyle, old-fashioned sailor dialect]
-
A.
hasBoldSingingStyle
Indicates that an entity performs singing in a manner characterized by confidence, power, and assertiveness.
-
B.
hasVocalStyleComparedTo
Indicates a comparison between entities based on the similarity or resemblance of their vocal style.
-
C.
hasDramaticStyle
Indicates that an entity employs or is characterized by a theatrical, emotionally intense, or striking manner of expression or presentation.
-
D.
hasSpokenStandard
Indicates that an entity has spoken using a recognized standard form of a language (e.g., standard dialect or official register).
-
E.
hasHookVocalStyle
Indicates that an entity (typically a musical work or performance) features a distinctive, catchy vocal delivery or refrain intended to serve as a memorable hook.
- F. None of above. chosen
Provenance (4 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_69f224dc84d0819081f1cb6f9127e6b1 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69fd09840ea88190a2e6d7e577ade717 |
completed | May 7, 2026, 9:52 p.m. |
| PD | Predicate disambiguation | batch_69fd064c49988190afadddbd04d7cb94 |
completed | May 7, 2026, 9:38 p.m. |
| PDg | Predicate description generation | batch_69fd098357348190a835c0b6d99857d2 |
completed | May 7, 2026, 9:52 p.m. |
Created at: April 29, 2026, 9:12 p.m.