Triple
T25436839
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tatsuko Kawashima |
E637397
|
entity |
| Predicate | maternal grandmother of |
P3524
|
FINISHED |
| Object | Prince Hisahito of Akishino |
—
|
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: Prince Hisahito of Akishino | Statement: [Tatsuko Kawashima, maternal grandmother of, Prince Hisahito of Akishino]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: maternal grandmother of Context triple: [Tatsuko Kawashima, maternal grandmother of, Prince Hisahito of Akishino]
-
A.
maternalGreatGrandmother
Indicates that one entity is the mother of another entity’s maternal grandmother (i.e., the person’s maternal great-grandmother).
-
B.
paternal grandmother
Indicates that one entity is the mother of the other entity’s father.
-
C.
grandmother
chosen
Indicates that one entity is the female parent of another entity's parent.
-
D.
maternalGrandsonOf
Indicates that one entity is the male child of the daughter of another entity (i.e., the other entity’s grandson through their maternal line).
-
E.
maternalGrandparents
Indicates the relationship between a person and the parents of that person’s mother.
- 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_69e75db6c97081908178383fa632b193 |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f5f6e0338c8190ace22e7a6239f68d |
completed | May 2, 2026, 1:06 p.m. |
| PD | Predicate disambiguation | batch_69f49377411c8190b2188de444d76795 |
completed | May 1, 2026, 11:50 a.m. |
Created at: April 21, 2026, 1:59 p.m.