Triple
T31320730
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kyoko Sakura |
E798727
|
entity |
| Predicate | fightsWitchesIn |
P172218
|
FINISHED |
| Object | Mitakihara City |
—
|
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: Mitakihara City | Statement: [Kyoko Sakura, fightsWitchesIn, Mitakihara City]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fightsWitchesIn Context triple: [Kyoko Sakura, fightsWitchesIn, Mitakihara City]
-
A.
diesFighting
Indicates that an entity dies as a direct result of engaging in a fight or combat.
-
B.
portraysFictionalCoven
Indicates that an entity depicts or represents a fictional coven, typically in a narrative or artistic context.
-
C.
fightsUsing
Indicates that one entity engages in combat or conflict by employing another entity as its weapon, tool, or method of fighting.
-
D.
hasFightSceneWith
Indicates that two entities participate together in a fight scene or combat sequence.
-
E.
covens
Indicates that one or more entities secretly cooperate or conspire together, often for a shared hidden or illicit purpose.
- F. None of above. chosen
Provenance (4 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_69f224e3238c8190b2291f50ea4962cd |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f6a9603b208190b3533ea2b441514c |
completed | May 3, 2026, 1:48 a.m. |
| PD | Predicate disambiguation | batch_69f6a7548eb48190a69b60a3c6ad53b9 |
completed | May 3, 2026, 1:39 a.m. |
| PDg | Predicate description generation | batch_69f6a915ead881909463ae46419c343e |
completed | May 3, 2026, 1:47 a.m. |
Created at: April 29, 2026, 9:15 p.m.