Triple
T28195042
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | FEL-1 |
E716419
|
entity |
| Predicate | seedingScheme |
P3620
|
FINISHED |
| Object | external seeding |
—
|
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: external seeding | Statement: [FEL-1, seedingScheme, external seeding]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: seedingScheme Context triple: [FEL-1, seedingScheme, external seeding]
-
A.
usesSeeding
chosen
Indicates that an entity employs a seeding process or strategy to initiate, distribute, or propagate something (such as data, content, or resources).
-
B.
determinesSeedingFor
Indicates that one entity is used to decide or assign the ranking, placement, or initial position (seeding) of another entity within a structured order or competition.
-
C.
partitionScheme
Indicates how a whole is divided into distinct parts or segments according to a specific organizing scheme.
-
D.
seedType
Indicates the specific kind or category of seed associated with an entity.
-
E.
seedProperty
Indicates that one entity serves as a seed or initial source from which the other entity’s properties, configuration, or content are derived or generated.
- 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_69efd6b612f48190a72012b520afbd10 |
completed | April 27, 2026, 9:35 p.m. |
| NER | Named-entity recognition | batch_69f642d058188190b71796a530a202f6 |
completed | May 2, 2026, 6:30 p.m. |
| PD | Predicate disambiguation | batch_69f63c6c1a948190b68c0f92c264cc0c |
completed | May 2, 2026, 6:03 p.m. |
Created at: April 27, 2026, 10:27 p.m.