Triple
T16284923
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dracunculus medinensis |
E395364
|
entity |
| Predicate | siteOfInfection |
P6647
|
FINISHED |
| Object | subcutaneous tissues |
—
|
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: subcutaneous tissues | Statement: [Dracunculus medinensis, siteOfInfection, subcutaneous tissues]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: siteOfInfection Context triple: [Dracunculus medinensis, siteOfInfection, subcutaneous tissues]
-
A.
infectionType
Indicates the specific category or nature of an infection associated with an entity or event.
-
B.
infectsTissue
chosen
Indicates that one entity (typically a pathogen or agent) invades and establishes itself within the tissue of another entity.
-
C.
infectionResult
Indicates that one entity causes or leads to a particular outcome, condition, or state as a result of an infection affecting another entity.
-
D.
woundLocation
Indicates the specific anatomical site on an entity’s body where a wound is present or occurred.
-
E.
infectionRequires
Indicates that the occurrence or establishment of an infection depends on the presence or fulfillment of a specified condition, factor, or prerequisite.
- 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_69d87f22c7248190a54c949738441e2e |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e24913a55081909a9a5a7a7f4806cc |
completed | April 17, 2026, 2:52 p.m. |
| PD | Predicate disambiguation | batch_69e219f68d308190b71c1601303f0628 |
completed | April 17, 2026, 11:31 a.m. |
Created at: April 10, 2026, 5:05 a.m.