Triple
T27539412
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wamesa language |
E695192
|
entity |
| Predicate | hasSpeakerNumberEstimate |
P1247
|
FINISHED |
| Object | several thousand speakers |
—
|
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: several thousand speakers | Statement: [Wamesa language, hasSpeakerNumberEstimate, several thousand speakers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSpeakerNumberEstimate Context triple: [Wamesa language, hasSpeakerNumberEstimate, several thousand speakers]
-
A.
hasApproximateTotalSpeakers
chosen
Indicates that an entity is associated with an estimated or roughly calculated number of total speakers, rather than an exact count.
-
B.
hasNumberOfSpeakersCategory
Indicates a classification of an entity based on the number of speakers associated with it, typically grouping it into predefined size categories.
-
C.
haveSpeakerPopulation
Indicates that an entity has a specified number or population size of people who speak a particular language.
-
D.
haveLimitedNumberOfSpeakers
Indicates that the language or communication system is used fluently by only a relatively small number of speakers.
-
E.
hasSpeakerDistribution
Indicates how speakers of a language or dialect are geographically or demographically distributed.
- 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_69ef538608b081908b9f659bb09d5e0f |
completed | April 27, 2026, 12:16 p.m. |
| NER | Named-entity recognition | batch_69f73ae120bc8190bff94d38d7a7a00d |
completed | May 3, 2026, 12:09 p.m. |
| PD | Predicate disambiguation | batch_69f73a38d0848190aa5139144b8561c6 |
completed | May 3, 2026, 12:06 p.m. |
Created at: April 27, 2026, 1:30 p.m.