Triple
T6696455
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nganasan language |
E152761
|
entity |
| Predicate | primaryCurrentSpeakers |
P18995
|
FINISHED |
| Object | elderly Nganasan people |
—
|
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: elderly Nganasan people | Statement: [Nganasan language, primaryCurrentSpeakers, elderly Nganasan people]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryCurrentSpeakers Context triple: [Nganasan language, primaryCurrentSpeakers, elderly Nganasan people]
-
A.
currentSpeakers
Indicates that the referenced entities are the ones who are presently speaking or holding the floor at a given moment.
-
B.
primarySpeakers
chosen
Indicates the entities that are the main or most significant speakers associated with another entity (such as an event, recording, or language).
-
C.
speakers
Indicates that one or more entities produce spoken language or vocal communication, typically addressing an audience or participating in a conversation.
-
D.
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.
-
E.
lastKnownSpeakers
Indicates the people or entities most recently known to use or speak a particular language.
- 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_69c6880687b08190805278b504d1c92c |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6b5ed99e48190970805225458ce82 |
completed | March 27, 2026, 4:53 p.m. |
| PD | Predicate disambiguation | batch_69c6ad0e1d348190af1762ea1951038e |
completed | March 27, 2026, 4:15 p.m. |
Created at: March 27, 2026, 2:05 p.m.