Triple
T520606
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chancellor of the Order of the Garter |
E10805
|
entity |
| Predicate | hasTitleInLanguage |
P15390
|
FINISHED |
| Object | Chancellor of the Most Noble Order of the Garter |
—
|
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: Chancellor of the Most Noble Order of the Garter | Statement: [Chancellor of the Order of the Garter, hasTitleInLanguage, Chancellor of the Most Noble Order of the Garter]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTitleInLanguage Context triple: [Chancellor of the Order of the Garter, hasTitleInLanguage, Chancellor of the Most Noble Order of the Garter]
-
A.
hasTitleInGerman
Indicates that an entity has a specific title or name expressed in the German language.
-
B.
hasLatinTitle
Indicates that an entity possesses a title or name expressed in Latin.
-
C.
containsTitle
Indicates that one entity includes or holds another entity’s title as part of its content or metadata.
-
D.
hasDutchTitle
Indicates that an entity possesses a title or name expressed in the Dutch language.
-
E.
hasIntertitlesLanguage
Indicates that the intertitles of a film or audiovisual work are presented in a specified language.
- F. None of above. chosen
Provenance (4 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_69a2e84b16c4819088d284c47c3a7968 |
completed | Feb. 28, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69a2f1a1817c8190a6cc8f423071d3ad |
completed | Feb. 28, 2026, 1:46 p.m. |
| PD | Predicate disambiguation | batch_69a2f016ba5c81909825b04e7525b4ab |
completed | Feb. 28, 2026, 1:39 p.m. |
| PDg | Predicate description generation | batch_69a2f1137e948190838303cdaa757a5a |
completed | Feb. 28, 2026, 1:43 p.m. |
Created at: Feb. 28, 2026, 1:12 p.m.