Triple
T5260271
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | the false prophet |
E118805
|
entity |
| Predicate | speechDescribedAs |
P40912
|
FINISHED |
| Object | speaks like a dragon |
—
|
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: speaks like a dragon | Statement: [the false prophet, speechDescribedAs, speaks like a dragon]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: speechDescribedAs Context triple: [the false prophet, speechDescribedAs, speaks like a dragon]
-
A.
speechType
Indicates the specific category or form of spoken or written communication that an utterance or speech act belongs to (e.g., question, statement, command).
-
B.
speechContent
Indicates that one entity expresses, conveys, or contains the spoken or written content associated with another entity’s act of speaking or communication.
-
C.
speechAlsoKnownAs
Indicates that a speech or spoken work is referred to by an alternative name, title, or alias.
-
D.
speechRegister
Indicates the level or style of formality in speech that one entity uses when addressing another.
-
E.
speakerFeatures
chosen
Indicates that certain characteristics, attributes, or properties are associated with a speaker in a given context.
- 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_69bd446a42c88190b7ecbef006561d55 |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd7bcced6881909bdb7ac5471a37fe |
completed | March 20, 2026, 4:54 p.m. |
| PD | Predicate disambiguation | batch_69bd77c55224819096c0bcfcfae79bd3 |
completed | March 20, 2026, 4:37 p.m. |
Created at: March 20, 2026, 1:50 p.m.