Triple
T34996183
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Naʼtche |
E1009535
|
entity |
| Predicate | lastKnownSpeakersDied |
P43860
|
FINISHED |
| Object | 20th century |
—
|
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: 20th century | Statement: [Naʼtche, lastKnownSpeakersDied, 20th century]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lastKnownSpeakersDied Context triple: [Naʼtche, lastKnownSpeakersDied, 20th century]
-
A.
lastNativeSpeakersDiedOut
chosen
Indicates that the final remaining native speakers of a language or dialect have died, resulting in the loss of native speech for that language.
-
B.
lastKnownSurvivorDiedIn
Indicates that the final remaining survivor associated with something died in a specified place or event.
-
C.
lastHolderDiedIn
Indicates that the most recent holder or possessor of something died in the specified place or during the specified event or time period.
-
D.
authorDateOfDeath
Indicates the date on which the author died.
-
E.
estimatedDateOfDeath
Indicates the date on which an entity is believed or calculated to have died, rather than a precisely known death date.
- 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_69f76dca50dc8190b71f39defe186be8 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f78710282c81909146dc0be91e983f |
completed | May 3, 2026, 5:34 p.m. |
| PD | Predicate disambiguation | batch_69f784162134819098413482ef52042f |
completed | May 3, 2026, 5:21 p.m. |
Created at: May 3, 2026, 4:01 p.m.