Triple
T38044020
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Atsumori |
E949565
|
entity |
| Predicate | featuresCharacterAsGhost |
P58281
|
FINISHED |
| Object | Taira no Atsumori |
E1264506
|
NE 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: Taira no Atsumori | Statement: [Atsumori, featuresCharacterAsGhost, Taira no Atsumori]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuresCharacterAsGhost Context triple: [Atsumori, featuresCharacterAsGhost, Taira no Atsumori]
-
A.
hasGhostCharacter
chosen
Indicates that an entity includes, features, or is associated with a character that is a ghost.
-
B.
effectOnGhosts
Indicates the influence or impact that something has on ghosts, such as how it alters their state, behavior, or abilities.
-
C.
featuresCharacterWith
Indicates that one entity (such as a work or product) includes or presents a particular character as part of its content.
-
D.
featuresReturningCharacterFrom
Indicates that a work includes the reappearance of a character who previously appeared in the referenced source work.
-
E.
returnsAsGhostTo
Indicates that an entity comes back after death in the form of a ghost to another entity or location.
- F. None of above.
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_69f76eff0bb0819084bc4e63997bd039 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_6a037df1223c8190a5d61e4f8e6fd613 |
completed | May 12, 2026, 7:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a415d30d0908190aa8f79c12876dae2 |
completed | June 28, 2026, 5:43 p.m. |
| PD | Predicate disambiguation | batch_6a037a1ad6c48190bfe35d350c1b4751 |
completed | May 12, 2026, 7:06 p.m. |
Created at: May 3, 2026, 4:20 p.m.