Triple
T5700545
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arshile Gorky |
E125647
|
entity |
| Predicate | birthName |
P65
|
FINISHED |
| Object | Vosdanig Adoian |
E120631
|
NE 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: Vosdanig Adoian | Statement: [Arshile Gorky, birthName, Vosdanig Adoian]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Vosdanig Adoian Context triple: [Arshile Gorky, birthName, Vosdanig Adoian]
-
A.
Garabet Balyan
Garabet Balyan was a prominent 19th-century Ottoman Armenian architect known for designing major imperial buildings in Istanbul in a blend of European and Ottoman styles.
-
B.
Vostanik Manoug Adoian
chosen
Vostanik Manoug Adoian, better known as Arshile Gorky, was an influential Armenian American painter whose work helped lay the foundations for Abstract Expressionism.
-
C.
Armen Tigranian
Armen Tigranian was an Armenian composer and conductor best known for his opera "Anoush," a landmark work in Armenian national music.
-
D.
Barsegh Kanachyan
Barsegh Kanachyan was an Armenian composer best known for writing the music to Armenia’s national anthem.
-
E.
Dikran Tulaine
Dikran Tulaine is an actor known for his role in the adventure film "The Librarian: Curse of the Judas Chalice."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69c0082c96988190b3a6a201edce472a |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c024540afc8190aee3760f71ea39c2 |
completed | March 22, 2026, 5:18 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c0a159077081909114b09f16ad2a1a |
completed | March 23, 2026, 2:11 a.m. |
Created at: March 22, 2026, 3:45 p.m.