Triple
T4306662
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ancylostoma duodenale |
E99969
|
entity |
| Predicate | hostEntrySite |
P2592
|
FINISHED |
| Object | skin of feet |
—
|
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: skin of feet | Statement: [Ancylostoma duodenale, hostEntrySite, skin of feet]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hostEntrySite Context triple: [Ancylostoma duodenale, hostEntrySite, skin of feet]
-
A.
hostConfederation
Indicates that an entity serves as the organizing or hosting confederation for a particular event, competition, or activity.
-
B.
host
chosen
Indicates that one entity provides space, resources, or services to accommodate, receive, or entertain another entity.
-
C.
hostsCompany
Indicates that one entity provides space, infrastructure, or support for a company to operate, be located, or hold activities.
-
D.
hostAssociation
Indicates a relationship in which one entity serves as the host or primary supporting environment for another entity.
-
E.
hostSelection
Indicates the choice or designation of a particular host from a set of possible hosts for a given purpose or interaction.
- 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_69b345528ebc8190b5abc7e95094792d |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b350bb78cc8190a850aca47d8711cf |
completed | March 12, 2026, 11:48 p.m. |
| PD | Predicate disambiguation | batch_69b347ff45cc8190b0cc335a94cc3d73 |
completed | March 12, 2026, 11:10 p.m. |
Created at: March 12, 2026, 11:09 p.m.