Triple
T29598158
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Natalie Bauer-Lechner |
E754362
|
entity |
| Predicate | wasCloseConfidanteOf |
P56457
|
FINISHED |
| Object | Gustav Mahler |
—
|
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: Gustav Mahler | Statement: [Natalie Bauer-Lechner, wasCloseConfidanteOf, Gustav Mahler]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wasCloseConfidanteOf Context triple: [Natalie Bauer-Lechner, wasCloseConfidanteOf, Gustav Mahler]
-
A.
confidantOf
chosen
Indicates a relationship in which one entity is trusted by another to receive and keep personal, private, or sensitive information.
-
B.
closelyInvolvedWith
Indicates a relationship in which one entity is deeply and actively engaged with another’s activities, decisions, or affairs.
-
C.
hasAllegedRelationshipWith
Indicates a claimed or suspected relationship between two entities that is not confirmed as factual.
-
D.
confidesIn
Indicates that one entity shares private, sensitive, or personal information or feelings with another entity in trust.
-
E.
hasPoliticalRelationshipWith
Indicates a political connection or association between two entities, such as alliances, rivalries, collaborations, or other forms of political interaction.
- 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_69f0ef84e5d08190a0df17f5930ceed3 |
completed | April 28, 2026, 5:33 p.m. |
| NER | Named-entity recognition | batch_69f66db95ed481908ec804df6d8b50a3 |
completed | May 2, 2026, 9:33 p.m. |
| PD | Predicate disambiguation | batch_69f6659d36208190b01412600a4ed57d |
completed | May 2, 2026, 8:59 p.m. |
Created at: April 28, 2026, 6:19 p.m.