Triple
T31917886
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shinobu Oshino |
E814884
|
entity |
| Predicate | hasBondWith |
P68132
|
FINISHED |
| Object | Koyomi Araragi |
—
|
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: Koyomi Araragi | Statement: [Shinobu Oshino, hasBondWith, Koyomi Araragi]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasBondWith Context triple: [Shinobu Oshino, hasBondWith, Koyomi Araragi]
-
A.
bondedWith
chosen
Indicates that two entities are joined by a strong, enduring connection or attachment, whether emotional, social, or structural.
-
B.
haveRelationshipWith
Indicates that one entity is in some form of defined relationship or association with another entity.
-
C.
hasContractWith
Indicates that one entity is bound by a formal contract or agreement with another entity.
-
D.
hasBondType
Indicates the specific kind of bond or connection that exists between two related entities.
-
E.
hasSocialTieWith
Indicates a social relationship or connection exists between two entities, such as friendship, acquaintance, or other interpersonal tie.
- 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_69f348f109d88190b5005372c53d2fcd |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69fd37b695c88190855801626f91c4cd |
completed | May 8, 2026, 1:09 a.m. |
| PD | Predicate disambiguation | batch_69fd374cccf08190a230e87164af5938 |
completed | May 8, 2026, 1:07 a.m. |
Created at: May 1, 2026, 12:02 a.m.