Triple
T3854136
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Unit 731 |
E85368
|
entity |
| Predicate | notablePathogen |
P31424
|
FINISHED |
| Object | Bacillus anthracis |
E52538
|
NE 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: Bacillus anthracis | Statement: [Unit 731, notablePathogen, Bacillus anthracis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bacillus anthracis Context triple: [Unit 731, notablePathogen, Bacillus anthracis]
-
A.
Bacillus anthracis
chosen
Bacillus anthracis is a Gram-positive, spore-forming bacterium that causes the disease anthrax in humans and animals.
-
B.
Yersinia pestis
Yersinia pestis is a highly virulent bacterium responsible for plague, including the historic pandemics of bubonic, septicemic, and pneumonic forms.
-
C.
Bacillus
Bacillus is a genus of rod-shaped, endospore-forming bacteria that includes both harmless environmental species and notable pathogens such as Bacillus anthracis.
-
D.
Yersinia
Yersinia is a genus of Gram-negative bacteria that includes several pathogenic species, most notably Yersinia pestis, the causative agent of plague.
-
E.
Vibrio cholerae
Vibrio cholerae is a Gram-negative, comma-shaped bacterium that causes the acute diarrheal disease cholera in humans.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69aed936de1c81908f91bed80f70abb2 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aef90e5f408190abf8353e153d1558 |
completed | March 9, 2026, 4:45 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b51231608c8190bbc5dc990fba1606 |
completed | March 14, 2026, 7:45 a.m. |
Created at: March 9, 2026, 3:19 p.m.