Triple
T38498382
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yente |
E919757
|
entity |
| Predicate | meddlesIn |
P10362
|
FINISHED |
| Object | romantic lives of Anatevka’s residents |
—
|
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: romantic lives of Anatevka’s residents | Statement: [Yente, meddlesIn, romantic lives of Anatevka’s residents]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: meddlesIn Context triple: [Yente, meddlesIn, romantic lives of Anatevka’s residents]
-
A.
intervenedIn
chosen
Indicates that an entity took action to alter, influence, or interrupt the course of an event, process, or interaction involving other entities.
-
B.
mediatesIn
Indicates that an entity serves as an intermediary or conduit through which an interaction, process, or effect occurs between other entities.
-
C.
intrudedInto
Indicates that one entity has entered or encroached upon another entity’s space, domain, or context without permission or in an unwelcome manner.
-
D.
canBeIntervenedBy
Indicates that an entity is susceptible to or eligible for intervention by another entity or agent.
-
E.
intervenesWhen
Indicates that one entity takes action to interrupt, mediate, or alter the course of another entity’s ongoing situation or process when certain conditions arise.
- 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_69f76e9ddd4481908f8c04439d848f9d |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fcd313e61c8190b174b331365b803f |
completed | May 7, 2026, 5:59 p.m. |
| PD | Predicate disambiguation | batch_69fcd1f6b2e08190bf0300ae7c9ae67a |
completed | May 7, 2026, 5:55 p.m. |
Created at: May 3, 2026, 4:31 p.m.