Triple
T26564320
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Przewalski’s horse |
E666333
|
entity |
| Predicate | canHybridizeWith |
P39441
|
FINISHED |
| Object | domestic horse |
—
|
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: domestic horse | Statement: [Przewalski’s horse, canHybridizeWith, domestic horse]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: canHybridizeWith Context triple: [Przewalski’s horse, canHybridizeWith, domestic horse]
-
A.
hasHybridization
chosen
Indicates that one entity participates in or results from a hybridization process involving another entity.
-
B.
hasHybridUses
Indicates that an entity is used in both traditional (e.g., physical or analog) and modern or alternative (e.g., digital, renewable, or mixed-mode) ways or contexts.
-
C.
canBeImplementedWith
Indicates that one entity is capable of being realized, executed, or fulfilled through the use or application of another entity.
-
D.
hasHybridSystem
Indicates that an entity is equipped with or incorporates a hybrid system, typically combining two or more different technologies or power sources.
-
E.
hasHybridSpecies
Indicates that one entity is a hybrid species that results from the combination or crossbreeding of another entity (or entities).
- 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_69ee9cf7e94481909f0d556b36e43572 |
completed | April 26, 2026, 11:17 p.m. |
| NER | Named-entity recognition | batch_69f6149cc0c88190aadaacfa45a2382e |
completed | May 2, 2026, 3:13 p.m. |
| PD | Predicate disambiguation | batch_69f602d7b1b0819095ddd3b5169f8ce2 |
completed | May 2, 2026, 1:57 p.m. |
Created at: April 27, 2026, 1:54 a.m.