Triple
T31797349
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ernst Göhner estate |
E811632
|
entity |
| Predicate | ownerAtTimeOfDeath |
P179257
|
FINISHED |
| Object | Ernst Göhner |
—
|
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: Ernst Göhner | Statement: [Ernst Göhner estate, ownerAtTimeOfDeath, Ernst Göhner]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ownerAtTimeOfDeath Context triple: [Ernst Göhner estate, ownerAtTimeOfDeath, Ernst Göhner]
-
A.
operatorAtTimeOfDisappearance
Indicates that an operator was responsible for or in control of something at the specific time when a disappearance occurred.
-
B.
associatedWithDeathOf
Indicates a relationship where one entity is connected in some relevant way to the death of another entity, such as by involvement, causation, or contextual association.
-
C.
onceDeceased
Indicates that an entity was previously dead at some point in time, regardless of its current state.
-
D.
afterDeathOf
Indicates that one event, state, or condition occurs subsequent to and as a result of the death of a specified entity.
-
E.
convertedAtDeath
Indicates that an entity adopted a new belief, status, or affiliation at or very near the moment of their death.
- 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_69f348e70d188190b4637c5509f81274 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f7201e241c819092d56a7bb99dc94d |
completed | May 3, 2026, 10:14 a.m. |
| PD | Predicate disambiguation | batch_69f71cc405c08190863565609a4c8499 |
completed | May 3, 2026, 10 a.m. |
| PDg | Predicate description generation | batch_69f71f8df5d48190944fbfbd9d573868 |
completed | May 3, 2026, 10:12 a.m. |
Created at: April 30, 2026, 11:41 p.m.