Triple
T36127273
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hubermann family |
E1044915
|
entity |
| Predicate | hasNarratorContext |
P144777
|
FINISHED |
| Object | narrated by Death |
—
|
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: narrated by Death | Statement: [Hubermann family, hasNarratorContext, narrated by Death]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNarratorContext Context triple: [Hubermann family, hasNarratorContext, narrated by Death]
-
A.
hasNarrativeContext
chosen
Indicates that an entity is associated with, or situated within, a particular narrative or storytelling context that frames its meaning or role.
-
B.
hasNarratorLineage
Indicates that one entity serves as the narrative ancestor or source from which another entity’s story, perspective, or narration is derived.
-
C.
hasNarration
Indicates that an entity provides spoken or written commentary or storytelling for another entity, such as a work, event, or scene.
-
D.
hasNarratorTribe
Indicates that the narrator belongs to or is a member of a specified tribe.
-
E.
hasCoNarrator
Indicates that two or more entities share the role of narrating the same work, event, or story together.
- 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_69f76e356c908190abc6ca1e6a05b011 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69ff70ecc1a481909571b18d56d982b8 |
completed | May 9, 2026, 5:37 p.m. |
| PD | Predicate disambiguation | batch_69ff70322a3c8190837840ea42cd3093 |
completed | May 9, 2026, 5:34 p.m. |
Created at: May 3, 2026, 4:08 p.m.