Triple
T10291098
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maya hieroglyphs |
E241364
|
entity |
| Predicate | decipheredBy |
P11828
|
FINISHED |
| Object | Yuri Knorozov |
E600284
|
NE 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: Yuri Knorozov | Statement: [Maya hieroglyphs, decipheredBy, Yuri Knorozov]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Yuri Knorozov Context triple: [Maya hieroglyphs, decipheredBy, Yuri Knorozov]
-
A.
Yuri Knorozov
chosen
Yuri Knorozov was a Russian linguist and epigrapher renowned for pioneering the successful decipherment of the Maya script.
-
B.
Nikolai Trubetzkoy
Nikolai Trubetzkoy was a Russian linguist and founding figure of structural phonology, best known for his work on phonological theory and the concept of the phoneme.
-
C.
Vladimir Koren
Vladimir Koren was a designer best known for creating the iconic state emblem of the Soviet Union.
-
D.
R. V. Gamkrelidze
R. V. Gamkrelidze is a Georgian mathematician known for his contributions to control theory and differential equations.
-
E.
Sergey Vavilov
Sergey Vavilov was a prominent Soviet physicist and academician, known for his work in physical optics and for serving as president of the USSR Academy of Sciences.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d381aaafc08190af475ef58dc16aba |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4d2d281348190bac00cf826689cd7 |
completed | April 7, 2026, 9:48 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d6f85dcbac8190a2ac66354010e328 |
completed | April 9, 2026, 12:52 a.m. |
Created at: April 6, 2026, 11:41 a.m.