Triple
T13131137
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roman medicine |
E311967
|
entity |
| Predicate | hasPublicHealthFeature |
P65774
|
FINISHED |
| Object | aqueducts |
—
|
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: aqueducts | Statement: [Roman medicine, hasPublicHealthFeature, aqueducts]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPublicHealthFeature Context triple: [Roman medicine, hasPublicHealthFeature, aqueducts]
-
A.
hasPublicHealthInfrastructure
chosen
Indicates that an entity possesses systems, facilities, and organizational structures dedicated to protecting and promoting public health.
-
B.
hasHealthCode
Indicates that an entity is associated with a specific health-related classification or status code.
-
C.
hasEmergencyUse
Indicates that an entity is authorized, designated, or configured for use specifically in emergency situations or conditions.
-
D.
hasEpidemiologyFeature
Indicates that an entity possesses a specific epidemiological characteristic or attribute related to the occurrence, distribution, or determinants of health conditions.
-
E.
hasInUniversePublicFeature
Indicates that an entity possesses a public-facing feature or characteristic within a specific fictional or defined universe.
- 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_69d806a9fe888190b081e2d9ea665d6c |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d981b27a8c81909a92ab7be5d3a7e9 |
completed | April 10, 2026, 11:03 p.m. |
| PD | Predicate disambiguation | batch_69d98043a74c81908648e6cd0b4c7f71 |
completed | April 10, 2026, 10:57 p.m. |
Created at: April 9, 2026, 9:07 p.m.