Triple
T3259818
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lake Albano |
E68381
|
entity |
| Predicate | emissaryBuiltBy |
P13567
|
FINISHED |
| Object | ancient Romans |
—
|
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: ancient Romans | Statement: [Lake Albano, emissaryBuiltBy, ancient Romans]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: emissaryBuiltBy Context triple: [Lake Albano, emissaryBuiltBy, ancient Romans]
-
A.
erectedBy
Indicates that something (such as a structure, monument, or installation) was constructed, set up, or raised by a particular agent or entity.
-
B.
commanderNationality
Indicates the national affiliation or citizenship of a given commander.
-
C.
originallyBuiltBy
chosen
Indicates that something was first constructed or created by a particular agent, organization, or entity.
-
D.
flagshipCarrierOf
Indicates that one entity serves as the primary or most prominent carrier (such as an airline or telecommunications provider) representing or associated with another entity, typically a country, brand, or organization.
-
E.
governingEmpireAtConstruction
Indicates the empire that held governing authority over a place or structure at the time it was constructed.
- 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_69ad858f74408190bcbd07f967cd7bd0 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69adafa673a481909b5024b4e0e1c2a7 |
completed | March 8, 2026, 5:19 p.m. |
| PD | Predicate disambiguation | batch_69ada41ae74081909a0d1d696be8e35e |
completed | March 8, 2026, 4:30 p.m. |
Created at: March 8, 2026, 3:09 p.m.