Triple
T35952759
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Uzbek Cyrillic alphabet |
E1039772
|
entity |
| Predicate | replacedEarlierScript |
P34177
|
FINISHED |
| Object | Uzbek Latin alphabet (1920s–1940s) |
—
|
NE NERFINISHED |
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: Uzbek Latin alphabet (1920s–1940s) | Statement: [Uzbek Cyrillic alphabet, replacedEarlierScript, Uzbek Latin alphabet (1920s–1940s)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: replacedEarlierScript Context triple: [Uzbek Cyrillic alphabet, replacedEarlierScript, Uzbek Latin alphabet (1920s–1940s)]
-
A.
replacedScript
chosen
Indicates that one script has been substituted for or superseded by another script.
-
B.
replacedEarlierModel
Indicates that one entity has taken the place of another entity that existed or was in use previously.
-
C.
replacedEarlierLight
Indicates that one light source has been substituted or superseded by another light source that existed or was installed earlier in time.
-
D.
laterUsedScript
Indicates that one entity adopted or employed the script of another entity at a later point in time.
-
E.
replacedEarlierTitle
Indicates that one title or designation has been superseded by an earlier title that it replaced in a sequence of naming or labeling.
- 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_69f76e25ea488190b7cee970b3e70382 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69fe189fec148190aeef51b417ba15b0 |
completed | May 8, 2026, 5:08 p.m. |
| PD | Predicate disambiguation | batch_69fe17285b0881908de7569d8dbd20bd |
completed | May 8, 2026, 5:02 p.m. |
Created at: May 3, 2026, 4:07 p.m.