Triple
T37979112
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tutelo |
E947502
|
entity |
| Predicate | lastFluentSpeakersDiedInCentury |
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: [Tutelo, lastFluentSpeakersDiedInCentury, 20th century]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lastFluentSpeakersDiedInCentury Context triple: [Tutelo, lastFluentSpeakersDiedInCentury, 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.
declineAsSpokenLanguageCentury
Indicates the century during which a language began or underwent significant decline in everyday spoken use.
-
C.
diedInCentury
Indicates that an entity’s death occurred during a specified century.
-
D.
flourishedUntilCentury
Indicates the last century during which an entity (such as a person, culture, or institution) was active, prominent, or at its peak before declining or ceasing to flourish.
-
E.
historicallySpokenIn
Indicates that a language was used for spoken communication in a particular place or region during a past historical period.
- 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_69f76ef7db908190bba6086673a32300 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fbc995dc2481908b3bd4217f8101e7 |
completed | May 6, 2026, 11:07 p.m. |
| PD | Predicate disambiguation | batch_69fbc8ee04f08190977b7ad70fc85896 |
completed | May 6, 2026, 11:04 p.m. |
Created at: May 3, 2026, 4:20 p.m.