Triple
T13343147
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dr. Thorkel |
E317876
|
entity |
| Predicate | treatsHumansAs |
P109101
|
FINISHED |
| Object | experimental subjects |
—
|
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: experimental subjects | Statement: [Dr. Thorkel, treatsHumansAs, experimental subjects]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: treatsHumansAs Context triple: [Dr. Thorkel, treatsHumansAs, experimental subjects]
-
A.
viewsNonHumansAs
Indicates how one entity perceives, interprets, or regards non-human entities (such as animals, objects, or systems).
-
B.
regardsDogsAs
Indicates that one entity holds a particular attitude, view, or treatment toward dogs.
-
C.
isHuman
Indicates that the subject entity possesses the defining characteristics or status of being a human.
-
D.
attitudeTowardHumanNature
Indicates an entity’s evaluative stance or belief about the fundamental characteristics and tendencies of human nature.
-
E.
treatsRightAs
Indicates that one entity provides medical or therapeutic treatment to another entity who is identified as the right-hand participant in the relationship.
- F. None of above. chosen
Provenance (4 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_69d806b5a3c08190b42c267fb092f98a |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d99e8839b48190b164414b418e756c |
completed | April 11, 2026, 1:06 a.m. |
| PD | Predicate disambiguation | batch_69d98f6e53d88190bd6aa42f69b10ffb |
completed | April 11, 2026, 12:01 a.m. |
| PDg | Predicate description generation | batch_69d99073e4708190843bda3a1ae78f43 |
completed | April 11, 2026, 12:06 a.m. |
Created at: April 9, 2026, 9:31 p.m.