Triple
T1629835
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Haunted Mansion |
E35231
|
entity |
| Predicate | usesHumor |
P14479
|
FINISHED |
| Object | yes |
—
|
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: yes | Statement: [Haunted Mansion, usesHumor, yes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesHumor Context triple: [Haunted Mansion, usesHumor, yes]
-
A.
hasHumorType
chosen
Indicates that an entity possesses or is characterized by a particular style, category, or type of humor.
-
B.
parodies
Indicates that one entity imitates another in an exaggerated or humorous way, often to criticize or comment on the original.
-
C.
enjoys
Indicates that one entity derives pleasure, satisfaction, or positive feelings from another entity or activity.
-
D.
hasCulturalReference
Indicates that one entity makes reference to, draws from, or is associated with the cultural content, symbols, or traditions represented by another entity.
-
E.
servesAtThePleasureOf
Indicates that one entity holds a position or role that can be terminated at any time by another entity, typically at the discretion or will of that other entity.
- 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_69a886036bc081909ff5de16dbe5e8ea |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a9431af5ac8190893133f1ae490142 |
completed | March 5, 2026, 8:47 a.m. |
| PD | Predicate disambiguation | batch_69a907c91c888190b6ed295c1a2e0977 |
completed | March 5, 2026, 4:34 a.m. |
Created at: March 4, 2026, 7:28 p.m.