Triple
T17577411
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mercury (Roman god) |
E428107
|
entity |
| Predicate | consort |
P13
|
FINISHED |
| Object | Larunda |
—
|
NE NERFINISHED |
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: Larunda | Statement: [Mercury (Roman god), consort, Larunda]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Larunda Context triple: [Mercury (Roman god), consort, Larunda]
-
A.
Larunda
chosen
Larunda is a nymph in Roman mythology, often associated with silence and the underworld, who becomes linked to the god Mercury as his companion.
-
B.
Luena
Luena is a city in eastern Angola that served as a significant site during the Angolan Civil War and later became known as the burial place of UNITA leader Jonas Savimbi.
-
C.
Chapecó
Chapecó is a major city in the state of Santa Catarina known as an important regional hub for agribusiness and food processing in southern Brazil.
-
D.
Tarija
Tarija is a city in southern Bolivia known for its colonial architecture, mild climate, and surrounding wine-producing valleys.
-
E.
Ossorio
Ossorio is a Spanish-origin surname notably borne by Filipino-American abstract expressionist artist Alfonso Ossorio.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d889e0385081908a04b66f4dd4bd0d |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e463ca76848190a7beb6deb4b0f1a4 |
completed | April 19, 2026, 5:10 a.m. |
Created at: April 10, 2026, 5:50 a.m.