Triple
T19688132
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tau |
E472765
|
entity |
| Predicate | hasUnicodeCodePointUppercase |
P44425
|
FINISHED |
| Object | U+03A4 |
—
|
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: U+03A4 | Statement: [Tau, hasUnicodeCodePointUppercase, U+03A4]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasUnicodeCodePointUppercase Context triple: [Tau, hasUnicodeCodePointUppercase, U+03A4]
-
A.
hasUnicodeCodePoint
chosen
Indicates that a character or symbol is associated with a specific numeric Unicode code point value.
-
B.
unicodeCodePoint
Indicates that a character or symbol is associated with a specific Unicode code point value in the Unicode standard.
-
C.
hasUppercase
Indicates that an entity contains at least one uppercase (capital) letter.
-
D.
hasUnicodeProperty
Indicates that an entity possesses a specific Unicode character property or set of properties (such as category, script, or other Unicode-defined attributes).
-
E.
hasUppercaseForm
Indicates that one textual entity is the uppercase version or representation of another textual entity.
- 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_69d8e515bef88190bc30781aea50537a |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6420d39688190ad3a84dbffce4ffe |
completed | April 20, 2026, 3:11 p.m. |
| PD | Predicate disambiguation | batch_69e53039ea808190a9106a53f564ab92 |
completed | April 19, 2026, 7:42 p.m. |
Created at: April 10, 2026, 1:45 p.m.