Triple
T22298986
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marie Syrkin |
E551202
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Syrkin |
—
|
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: Syrkin | Statement: [Marie Syrkin, familyName, Syrkin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Syrkin Context triple: [Marie Syrkin, familyName, Syrkin]
-
A.
Syrkin
chosen
Syrkin is a Jewish surname most notably associated with Nachman Syrkin, a pioneering theorist of socialist Zionism.
-
B.
Syrdon
Syrdon is a cunning and often mischievous trickster figure from the Caucasian Nart sagas, known for his wit, guile, and disruptive antics among the Nart heroes.
-
C.
Yunaska
Yunaska is the maiden surname of Lara Trump, who is married to Eric Trump, son of former U.S. President Donald Trump.
-
D.
Shiskine
Shiskine is a small village on the Isle of Arran in Scotland, known for its rural setting and close-knit community.
-
E.
Sidyma
Sidyma was an ancient Lycian city in southwestern Anatolia, known for its rock-cut tombs and membership in the Lycian League.
- 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_69e11e45fb848190a1b2ae21296e3a5f |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15722c3348190b63eb49764ef132d |
completed | April 29, 2026, 12:56 a.m. |
Created at: April 16, 2026, 8:41 p.m.