Triple
T16127109
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Knock |
E391299
|
entity |
| Predicate | apparitionType |
P99195
|
FINISHED |
| Object | silent apparition |
—
|
LITERAL 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: silent apparition | Statement: [Knock, apparitionType, silent apparition]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: apparitionType Context triple: [Knock, apparitionType, silent apparition]
-
A.
associatedWithApparition
Indicates a relationship where something is linked or connected to an apparition, such as being caused by, accompanying, or characterizing that apparition.
-
B.
apparitionsRecognizedBy
Indicates that certain apparitions are acknowledged, identified, or accepted as genuine by a particular person, group, or authority.
-
C.
reportedApparitionEntity
Indicates that an entity has been reported or described as an apparition in some account or observation.
-
D.
typeOfSpirit
chosen
Indicates the specific kind or category of spirit (e.g., ghost, demon, angel) that an entity belongs to.
-
E.
apparitionsDate
Indicates the date on which the apparitions are reported or believed to have occurred.
- 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_69d87f1bb0988190b490d273dbf3fd03 |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e20205bed48190a6930439738da191 |
completed | April 17, 2026, 9:48 a.m. |
| PD | Predicate disambiguation | batch_69e1828518c48190a8ef3aaa46a1f639 |
completed | April 17, 2026, 12:44 a.m. |
Created at: April 10, 2026, 5 a.m.