Triple
T36401700
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Big Five animals |
E896647
|
entity |
| Predicate | includesHerbivore |
P28386
|
FINISHED |
| Object | African elephant |
—
|
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: African elephant | Statement: [Big Five animals, includesHerbivore, African elephant]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: includesHerbivore Context triple: [Big Five animals, includesHerbivore, African elephant]
-
A.
isHerbivorousOrOmnivorous
Indicates that an entity either primarily eats plants (herbivorous) or consumes both plant and animal matter (omnivorous).
-
B.
isCarnivorous
Indicates that an entity feeds primarily or exclusively on other animals.
-
C.
includesSpeciesWithDiet
chosen
Indicates that a group, area, or collection contains at least one species characterized by a specified type of diet.
-
D.
animalDietProvided
Indicates that food appropriate to an animal’s dietary needs is supplied to it.
-
E.
isRuminant
Indicates that an animal chews cud as part of a multi-chambered stomach digestive process.
- 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_69f76e53b81081908d3b81860593f38a |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a037c8d06cc8190ab6a5e18d9d2571e |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a0a54cc8190868c1bfa1590d1a6 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:10 p.m.