Triple
T18758743
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Orontid dynasty |
E458715
|
entity |
| Predicate | ruled |
P760
|
FINISHED |
| Object | Sophene |
—
|
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: Sophene | Statement: [Orontid dynasty, ruled, Sophene]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sophene Context triple: [Orontid dynasty, ruled, Sophene]
-
A.
Sophene
chosen
Sophene was an ancient historical region in the Armenian Highlands, known as a frontier kingdom and later province situated between Armenia and Mesopotamia.
-
B.
Calipha
Calipha is an alternative English transliteration of the Arabic title "Khalifa," historically used for the leader or successor in Islamic governance and religious authority.
-
C.
Safira
Safira is a feminine given name, often associated with the word "sapphire" and used in various cultures.
-
D.
Siryn
Siryn is a Marvel Comics mutant superhero known for her powerful sonic scream and affiliation with teams like X-Force.
-
E.
Mirrione
Mirrione is the surname of American film editor Stephen Mirrione, known for his work on acclaimed movies such as "Traffic" and "Ocean's Eleven."
- 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_69d8d395dba0819087568404508590cb |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e579f42d0881909bd9ca9c7916516a |
completed | April 20, 2026, 12:57 a.m. |
Created at: April 10, 2026, 11:52 a.m.