Triple
T9375965
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Karma Police |
E225645
|
entity |
| Predicate | isHaunting |
P15512
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [Karma Police, isHaunting, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isHaunting Context triple: [Karma Police, isHaunting, true]
-
A.
haunts
chosen
Indicates that one entity persistently appears in, lingers around, or psychologically troubles another entity or place, often in a recurring or unsettling way.
-
B.
hasGhostCharacter
Indicates that an entity includes, features, or is associated with a character that is a ghost.
-
C.
containsSupernaturalElement
Indicates that the subject involves or features a supernatural, magical, or otherworldly element beyond normal natural laws.
-
D.
hasHorrorElements
Indicates that something contains features, themes, or stylistic aspects characteristic of the horror genre.
-
E.
deathAttracting
Indicates a relationship where one entity’s death draws, lures, or otherwise causes another entity to come closer or be attracted.
- 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_69ca842d8ee88190aaaa639aa953185d |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd50aa3d008190836d0fde840da7d2 |
completed | April 1, 2026, 5:06 p.m. |
| PD | Predicate disambiguation | batch_69cc7a6c733881908aa3070830c2100b |
completed | April 1, 2026, 1:52 a.m. |
Created at: March 30, 2026, 7:44 p.m.