Triple
T2697584
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mr. Secretary |
E58547
|
entity |
| Predicate | usedInSpeech |
P15075
|
FINISHED |
| Object | direct address |
—
|
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 address | Statement: [Mr. Secretary, usedInSpeech, direct address]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedInSpeech Context triple: [Mr. Secretary, usedInSpeech, direct address]
-
A.
usedInSpokenForm
chosen
Indicates that something (such as a word, name, or expression) is employed in spoken language or oral communication.
-
B.
usedInLanguage
Indicates that something (such as a word, expression, or symbol) is employed or occurs within a particular language.
-
C.
isSpokenAlong
Indicates that something (typically a language or dialect) is used or spoken in the regions or areas that follow a particular path, boundary, or route.
-
D.
linguisticUsage
Indicates how a linguistic form, expression, or construction is used in language, such as its typical context, function, or register.
-
E.
speaksIn
Indicates that an entity uses or expresses itself in a particular language or medium when speaking.
- 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_69ab4ac269e481909cb317d79e68b75b |
completed | March 6, 2026, 9:44 p.m. |
| NER | Named-entity recognition | batch_69abda322af48190833b8a3c006db236 |
completed | March 7, 2026, 7:56 a.m. |
| PD | Predicate disambiguation | batch_69abd81ea5d88190ab5c8f8b8064b931 |
completed | March 7, 2026, 7:47 a.m. |
Created at: March 6, 2026, 9:55 p.m.