Triple
T30933368
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kelly (original The Office character archetype, loosely) |
E788053
|
entity |
| Predicate | focusOfHumor |
P177263
|
FINISHED |
| Object | celebrity gossip |
—
|
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: celebrity gossip | Statement: [Kelly (original The Office character archetype, loosely), focusOfHumor, celebrity gossip]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: focusOfHumor Context triple: [Kelly (original The Office character archetype, loosely), focusOfHumor, celebrity gossip]
-
A.
humourTarget
chosen
Indicates that one entity is the object or focus of another entity’s humor, such as jokes, teasing, or comedic commentary.
-
B.
humorSetting
Indicates a relationship where one entity specifies or controls the level, style, or presence of humor applied to another entity or context.
-
C.
hasHumorFunction
Indicates that something serves a humorous role or purpose, such as eliciting amusement, laughter, or comedic effect.
-
D.
usedForHumor
Indicates that something is employed with the intention of being funny, amusing, or comical.
-
E.
humorReliesOn
Indicates that one entity’s humor depends on, is based on, or draws its effect from another 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_69f224c0b7fc819090cb89df60d23653 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f78c61ed4c8190ad84c918fa9af55a |
completed | May 3, 2026, 5:56 p.m. |
| PD | Predicate disambiguation | batch_69f78b8cb3a881909ebaac1b503988c2 |
completed | May 3, 2026, 5:53 p.m. |
Created at: April 29, 2026, 8:52 p.m.