Triple
T23752676
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eliza Thornberry |
E587012
|
entity |
| Predicate | associatedAnimalCompanion |
P24316
|
FINISHED |
| Object | chimpanzee Darwin |
—
|
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: chimpanzee Darwin | Statement: [Eliza Thornberry, associatedAnimalCompanion, chimpanzee Darwin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedAnimalCompanion Context triple: [Eliza Thornberry, associatedAnimalCompanion, chimpanzee Darwin]
-
A.
companionAnimals
chosen
Indicates a relationship where one entity keeps or cares for another entity as a pet or companion animal.
-
B.
associatedWithAnimal
Indicates a relationship where an entity has a connection, link, or relevance to an animal.
-
C.
animalTypeLoved
Indicates that one entity loves or is especially fond of animals of a particular type.
-
D.
animalAssociation
Indicates a relationship in which one animal is associated with another animal or entity, such as through interaction, co-occurrence, or ecological linkage.
-
E.
animalComponent
Indicates that one entity is a physical or functional part, piece, or constituent of an animal.
- 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_69e2490a0eec81908cdef8a862828d7a |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1bcc3a06c81908e8a6e1f531c73bc |
completed | April 29, 2026, 8:09 a.m. |
| PD | Predicate disambiguation | batch_69f155f012808190a4b1cbc155558ade |
completed | April 29, 2026, 12:50 a.m. |
Created at: April 17, 2026, 7:13 p.m.