Triple
T188908
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Unicode |
E3674
|
entity |
| Predicate | maintainedBy |
P86
|
FINISHED |
| Object | Unicode Consortium |
E24737
|
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: Unicode Consortium | Statement: [Unicode, maintainedBy, Unicode Consortium]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Unicode Consortium Context triple: [Unicode, maintainedBy, Unicode Consortium]
-
A.
Unicode Consortium
chosen
The Unicode Consortium is a non-profit organization that standardizes the representation of text and symbols in digital systems worldwide through the Unicode Standard.
-
B.
Unicode
Unicode is a universal character encoding standard that assigns unique code points to virtually all written scripts, symbols, and emojis used in modern computing.
-
C.
Basic Multilingual Plane
The Basic Multilingual Plane is the primary block of the Unicode standard that contains the most commonly used characters for modern scripts and symbols.
-
D.
Unicode Scalar Values
Unicode Scalar Values are the set of valid Unicode code points (excluding surrogate code points) that uniquely identify abstract characters in the Unicode standard.
-
E.
UTF-32
UTF-32 is a fixed-length Unicode character encoding that represents each code point using 32 bits, providing simple indexing at the cost of higher memory usage.
- 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_69a2548debd48190ae3a06d6e65b53c6 |
completed | Feb. 28, 2026, 2:35 a.m. |
| NER | Named-entity recognition | batch_69a2594abeec8190a48f36817e647fcd |
completed | Feb. 28, 2026, 2:56 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a3161ab0548190b4c0ed74a79cea46 |
completed | Feb. 28, 2026, 4:21 p.m. |
Created at: Feb. 28, 2026, 2:41 a.m.