Triple
T34569510
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Peurion |
E887584
|
entity |
| Predicate | hasParentGrape |
P200560
|
FINISHED |
| Object | Heunisch Weiss |
—
|
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: Heunisch Weiss | Statement: [Peurion, hasParentGrape, Heunisch Weiss]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasParentGrape Context triple: [Peurion, hasParentGrape, Heunisch Weiss]
-
A.
hasParentsFrom
Indicates that an entity’s parents originate from or are associated with a specified place, group, or category.
-
B.
isUndopedParentOf
Indicates a parent-child relationship where the parent entity is in an undoped (unmodified or impurity-free) state relative to its child.
-
C.
hasNotableParent
Indicates that an entity has a parent who is distinguished, prominent, or otherwise notable.
-
D.
hasParentMaterial
Indicates that one entity is derived from, formed in, or directly associated with another entity that serves as its original or underlying material.
-
E.
sometimesHasParent
Indicates that an entity has a particular parent entity in some, but not necessarily all, situations or contexts.
- F. None of above. chosen
Provenance (4 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_69f349d1a5fc81908557a46875b2f157 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69ff965f9be48190b015b788207be676 |
completed | May 9, 2026, 8:17 p.m. |
| PD | Predicate disambiguation | batch_69ff95d3015c8190b9d293fe31b859c3 |
completed | May 9, 2026, 8:15 p.m. |
| PDg | Predicate description generation | batch_69ff965eef90819097499d1f0542378c |
completed | May 9, 2026, 8:17 p.m. |
Created at: May 1, 2026, 2:02 a.m.