Triple
T30925753
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sexual Harassment (The Office U.S.) |
E787849
|
entity |
| Predicate | featuresFictionalCompany |
P22830
|
FINISHED |
| Object | Dunder Mifflin |
—
|
NE NERFINISHED |
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: Dunder Mifflin | Statement: [Sexual Harassment (The Office U.S.), featuresFictionalCompany, Dunder Mifflin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuresFictionalCompany Context triple: [Sexual Harassment (The Office U.S.), featuresFictionalCompany, Dunder Mifflin]
-
A.
featuresCompany
Indicates that one entity prominently presents, highlights, or showcases a company, typically as part of content, listings, or promotional material.
-
B.
fictionalOrganizationFeatured
chosen
Indicates that a fictional organization is prominently presented or plays a significant role within a given work or context.
-
C.
fictionalCorporation
Indicates that an entity is a corporation that exists only in fiction rather than in the real world.
-
D.
featuresSpyAgency
Indicates that a work includes or prominently involves a spy agency as part of its content or storyline.
-
E.
featuresSign
Indicates that an entity includes, displays, or incorporates a particular sign as part of its appearance, content, or design.
- 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_69f224bfaca88190b9d0dfcc86297fe9 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_6a0041860fd081908623ef9fd40a9775 |
completed | May 10, 2026, 8:27 a.m. |
| PD | Predicate disambiguation | batch_6a00414b01488190a312adb3b25d69cf |
completed | May 10, 2026, 8:26 a.m. |
Created at: April 29, 2026, 8:51 p.m.