Triple
T32080689
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ZH |
E819286
|
entity |
| Predicate | capitalizedForm |
P72382
|
FINISHED |
| Object | ZH |
—
|
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: ZH | Statement: [ZH, capitalizedForm, ZH]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: capitalizedForm Context triple: [ZH, capitalizedForm, ZH]
-
A.
capitalizedOn
Indicates that one entity took advantage of, exploited, or made beneficial use of an opportunity, situation, or resource provided or created by another entity.
-
B.
preferredCapitalization
chosen
Indicates the specific way a term’s letters should be capitalized when it is written or displayed.
-
C.
isCapitalised
Indicates that a given string or word is written with its first letter in uppercase (and the rest in lowercase, if applicable).
-
D.
usesCapitalization
Indicates that one entity applies specific capitalization (such as upper/lower case or title case) to another entity, typically a string or text element.
-
E.
capitalizationFocus
Indicates a relationship where attention or emphasis is placed on the use, style, or correctness of capitalization in text.
- 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_69f348ff8ef88190931c08ba530a36bc |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69fd2839880c819099a7a89783f2270e |
completed | May 8, 2026, 12:03 a.m. |
| PD | Predicate disambiguation | batch_69fd23dc5da48190ae8ba08947d34956 |
completed | May 7, 2026, 11:44 p.m. |
Created at: May 1, 2026, 12:24 a.m.