Triple
T26442841
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | George of Austria |
E665133
|
entity |
| Predicate | canonTitle |
P15922
|
FINISHED |
| Object | bishop of Liège |
—
|
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: bishop of Liège | Statement: [George of Austria, canonTitle, bishop of Liège]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: canonTitle Context triple: [George of Austria, canonTitle, bishop of Liège]
-
A.
cultTitleOf
Indicates that the subject holds a religious or cultic title or honorific associated with the object.
-
B.
canonicalReferenceTitle
Indicates that one entity serves as the standard or authoritative title by which another entity is formally referenced or identified.
-
C.
titleInKanji
Indicates that one entity is the title of another entity written specifically in Kanji characters.
-
D.
titleOnTheLine
Indicates that a title or heading is positioned directly on a specific line (such as a line of text, a boundary, or a graphical line) rather than above, below, or separate from it.
-
E.
titles
chosen
Indicates that one entity holds a formal title, designation, or name associated with another 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_69ee883c851881909e2ab04efbb3c5fe |
completed | April 26, 2026, 9:48 p.m. |
| NER | Named-entity recognition | batch_69f6121d00d48190b64b88a7d75c6e3b |
completed | May 2, 2026, 3:02 p.m. |
| PD | Predicate disambiguation | batch_69f60b89cc048190a9feb24466006be0 |
completed | May 2, 2026, 2:34 p.m. |
Created at: April 26, 2026, 11:59 p.m.