Triple
T29465013
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Béla Szőkefalvi-Nagy |
E747351
|
entity |
| Predicate | hasCanonicalNameVariant |
P19207
|
FINISHED |
| Object | Bela Szokefalvi-Nagy |
—
|
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: Bela Szokefalvi-Nagy | Statement: [Béla Szőkefalvi-Nagy, hasCanonicalNameVariant, Bela Szokefalvi-Nagy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCanonicalNameVariant Context triple: [Béla Szőkefalvi-Nagy, hasCanonicalNameVariant, Bela Szokefalvi-Nagy]
-
A.
hasCanonicalNameForm
chosen
Indicates that an entity is associated with its standard or officially recognized name form.
-
B.
hasNameVariantType
Indicates that one name is a specific type or variant of another name, such as an alias, abbreviation, or alternative spelling.
-
C.
hasOfficialNameVariant
Indicates that an entity has an alternative official form or version of its name.
-
D.
hasCanonicalTerm
Indicates that one term in a set is designated as the standard or authoritative form used to represent a concept or entity.
-
E.
hasCanonicalVersionBy
Indicates that one entity is the officially recognized or standard version of another entity, as established or authored by a specific source or agent.
- 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_69f0bd4125f88190b56104591351619c |
completed | April 28, 2026, 1:59 p.m. |
| NER | Named-entity recognition | batch_69fd68abf52881909c5a390c362b7c59 |
completed | May 8, 2026, 4:38 a.m. |
| PD | Predicate disambiguation | batch_69fd6812d0c88190930d8fa2d4b92490 |
completed | May 8, 2026, 4:35 a.m. |
Created at: April 28, 2026, 3:52 p.m.