Triple
T1210988
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Haden mango |
E25998
|
entity |
| Predicate | roleInBreeding |
P23046
|
FINISHED |
| Object | parent of many modern mango cultivars |
—
|
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: parent of many modern mango cultivars | Statement: [Haden mango, roleInBreeding, parent of many modern mango cultivars]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleInBreeding Context triple: [Haden mango, roleInBreeding, parent of many modern mango cultivars]
-
A.
reproductiveRole
chosen
Indicates the specific function or part an entity plays in biological reproduction within a reproductive process or system.
-
B.
roleInvolves
Indicates that a particular role includes or requires participation in a specified activity, responsibility, or function.
-
C.
breed
Indicates that an organism reproduces to generate offspring, typically with another organism of the same species.
-
D.
reproductiveBehavior
Indicates the actions, strategies, and interactions involved in an organism’s mating and reproduction processes.
-
E.
reproductiveType
Indicates the mode or strategy by which an organism reproduces or generates offspring.
- 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_69a4948331fc8190b531ac9bec71c491 |
completed | March 1, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69a4bde581308190bbe30683bf6c48c3 |
completed | March 1, 2026, 10:29 p.m. |
| PD | Predicate disambiguation | batch_69a4bb6078088190ba0221ae3368416c |
completed | March 1, 2026, 10:19 p.m. |
Created at: March 1, 2026, 7:46 p.m.