Triple
T19525721
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Washoe language |
E488512
|
entity |
| Predicate | hasSpeakerStatus |
P136643
|
FINISHED |
| Object | very few fluent speakers remaining |
—
|
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: very few fluent speakers remaining | Statement: [Washoe language, hasSpeakerStatus, very few fluent speakers remaining]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSpeakerStatus Context triple: [Washoe language, hasSpeakerStatus, very few fluent speakers remaining]
-
A.
hasSpeakerType
Indicates that an entity functions in a particular role or category as a speaker (e.g., narrator, character, announcer) within a given context.
-
B.
hasSpeech
Indicates that an entity produces, delivers, or is associated with a spoken utterance or verbal expression.
-
C.
hasMainSpeaker
Indicates that one entity serves as the primary or principal speaker associated with another entity, such as an event, recording, or presentation.
-
D.
numberOfSpeakersStatus
Indicates the status or condition of information about how many speakers are involved (e.g., whether the number of speakers is known, estimated, missing, or otherwise qualified).
-
E.
hasSpeakersIn
Indicates that an entity (such as an event, conference, or session) includes or is associated with speakers located in or belonging to a specified place or group.
- 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_69d8e8da8bec819081f400199491ccc3 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e6363aeb8c8190be2bdd73e421af96 |
completed | April 20, 2026, 2:20 p.m. |
| PD | Predicate disambiguation | batch_69e514c9c00481909b76bda67957e58b |
completed | April 19, 2026, 5:45 p.m. |
| PDg | Predicate description generation | batch_69e51a23300c8190988552491d9783d7 |
completed | April 19, 2026, 6:08 p.m. |
Created at: April 10, 2026, 1:41 p.m.