Triple
T33776966
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Henri Farman |
E865547
|
entity |
| Predicate | improvedDesignOf |
P6555
|
FINISHED |
| Object | Voisin biplane |
—
|
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: Voisin biplane | Statement: [Henri Farman, improvedDesignOf, Voisin biplane]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: improvedDesignOf Context triple: [Henri Farman, improvedDesignOf, Voisin biplane]
-
A.
improvesIn
Indicates that one entity causes or contributes to an increase in quality, performance, or effectiveness in another entity or context.
-
B.
improvesOn
chosen
Indicates that one entity enhances, refines, or performs better than another entity, typically by addressing its limitations or increasing its effectiveness.
-
C.
designedFeature
Indicates that one entity is a feature or component intentionally planned, created, or specified by another entity as part of a design.
-
D.
testedDesignFeature
Indicates that a specific design feature has been subjected to a test or evaluation process.
-
E.
redesigned
Indicates that an entity has been modified or created anew in terms of its structure, appearance, or functionality, replacing a previous design.
- 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_69f3498df6f88190bf9647ea4e4a956e |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f6ffbad8848190867c2988c0ceb84f |
completed | May 3, 2026, 7:56 a.m. |
| PD | Predicate disambiguation | batch_69f6fc5740fc81909774a4f65201a3ff |
completed | May 3, 2026, 7:42 a.m. |
Created at: May 1, 2026, 1:45 a.m.