Triple
T3939218
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Patriarch of All Romania |
E91990
|
entity |
| Predicate | hasCanonicalRank |
P21161
|
FINISHED |
| Object | patriarch |
—
|
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: patriarch | Statement: [Patriarch of All Romania, hasCanonicalRank, patriarch]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCanonicalRank Context triple: [Patriarch of All Romania, hasCanonicalRank, patriarch]
-
A.
hasCanonicalRelevance
Indicates that something is considered standard, authoritative, or centrally important within an established canon or reference framework.
-
B.
hasCanonicalNumber
Indicates that an entity is associated with its officially recognized or standard reference number.
-
C.
hasCanonicalReference
Indicates that one entity serves as the authoritative or standard reference source for another entity.
-
D.
hasCanonicalPosition
chosen
Indicates that an entity occupies a standard, officially recognized, or authoritative position or location within a defined structure or system.
-
E.
hasComparableRank
Indicates that two entities hold positions or levels that are equivalent or similar in rank within a given hierarchy or system.
- 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_69aed965502c8190904ebad1203a4ae8 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aeedfb12b88190a6ca6574b1aadb6e |
completed | March 9, 2026, 3:57 p.m. |
| PD | Predicate disambiguation | batch_69aee7625ad4819097e4e8a168c19274 |
completed | March 9, 2026, 3:29 p.m. |
Created at: March 9, 2026, 3:24 p.m.