Triple
T20202999
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Deimos (mythology) |
E493270
|
entity |
| Predicate | romanEquivalent |
P6662
|
FINISHED |
| Object | Metus |
—
|
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: Metus | Statement: [Deimos (mythology), romanEquivalent, Metus]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Metus Context triple: [Deimos (mythology), romanEquivalent, Metus]
-
A.
Metus
chosen
Metus is the Roman personification and god of fear and dread, corresponding to the Greek deity Phobos.
-
B.
Megarus
Megarus is a lesser-known figure in Greek mythology, recognized as one of the many sons of the chief Olympian god Zeus.
-
C.
Auxerrois
Auxerrois refers to a person from the city of Auxerre in France, and by extension can also denote things associated with that city.
-
D.
Auxerrois
Auxerrois is a French red wine grape variety more commonly known as Malbec, widely used in robust, deeply colored wines.
-
E.
Auxerrois
Auxerrois is a white wine grape variety from northeastern France, particularly associated with Alsace, known for producing soft, aromatic wines often blended into regional sparkling and still wines.
- 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_69da6269614c8190bb40475d9d477358 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e66d8ec73c8190b630599c5ceb22ac |
completed | April 20, 2026, 6:16 p.m. |
Created at: April 11, 2026, 11:38 p.m.