Triple
T35332115
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Margrave of Austria |
E1020347
|
entity |
| Predicate | precedesInTitleHistory |
P2939
|
FINISHED |
| Object | Duke of Austria |
—
|
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: Duke of Austria | Statement: [Margrave of Austria, precedesInTitleHistory, Duke of Austria]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: precedesInTitleHistory Context triple: [Margrave of Austria, precedesInTitleHistory, Duke of Austria]
-
A.
previousTitle
chosen
Indicates that one title held or used by an entity directly preceded another title in sequence or time.
-
B.
precededByTitleInRank
Indicates that one title holds a higher rank and comes before another title in an ordered hierarchy.
-
C.
predecessorTitleContext
Indicates that the relationship specifies the contextual circumstances (such as role, period, or setting) under which a predecessor’s title is relevant or applies.
-
D.
predecessorTitleHolder
Indicates that one entity previously held a particular title or position before another entity.
-
E.
predecessorTitlePattern
Indicates the pattern or template used to represent the title of an entity’s immediate predecessor in a sequence or hierarchy.
- 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_69f76deacf4481908e7735a5a7715b0a |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69fd864235b481908738dbb69556bc62 |
completed | May 8, 2026, 6:44 a.m. |
| PD | Predicate disambiguation | batch_69fd8373b6bc819091c554f29ee17fec |
completed | May 8, 2026, 6:32 a.m. |
Created at: May 3, 2026, 4:03 p.m.