Triple
T37439928
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Matilda of Brunswick-Lüneburg |
E930385
|
entity |
| Predicate | paternalGreatGreatGrandfather |
P47031
|
FINISHED |
| Object | Henry V, Duke of Bavaria |
—
|
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: Henry V, Duke of Bavaria | Statement: [Matilda of Brunswick-Lüneburg, paternalGreatGreatGrandfather, Henry V, Duke of Bavaria]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: paternalGreatGreatGrandfather Context triple: [Matilda of Brunswick-Lüneburg, paternalGreatGreatGrandfather, Henry V, Duke of Bavaria]
-
A.
paternalGreatGrandfatherOf
Indicates that one person is the father of another person's paternal grandfather.
-
B.
paternalGreatGrandmother
Indicates that one entity is the father’s father’s mother of another entity.
-
C.
paternalGreatGrandparentOf
Indicates that one person is the father of another person’s grandparent, making him that person’s paternal great-grandparent.
-
D.
greatGreatGrandfather
chosen
Indicates that one person is the father of another person's great-grandparent.
-
E.
paternalGrandchildOf
Indicates that one entity is the grandchild of another through the latter’s son (i.e., via the paternal line).
- 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_69f76ebfdcb8819098562ff3db673b04 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fb92efc5948190a040ba2028bab964 |
completed | May 6, 2026, 7:13 p.m. |
| PD | Predicate disambiguation | batch_69fb8d0b52588190bb29937a43b99b5e |
completed | May 6, 2026, 6:48 p.m. |
Created at: May 3, 2026, 4:17 p.m.