Triple
T19928707
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | מְפִיבֹשֶׁת |
E478994
|
entity |
| Predicate | servedBy |
P82
|
FINISHED |
| Object | Ziba |
—
|
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: Ziba | Statement: [מְפִיבֹשֶׁת, servedBy, Ziba]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ziba Context triple: [מְפִיבֹשֶׁת, servedBy, Ziba]
-
A.
Ziba
chosen
Ziba is a biblical figure in the Old Testament, known as the former servant of Saul who later served Mephibosheth and interacted with King David during Absalom’s rebellion.
-
B.
Ifra Hormizd
Ifra Hormizd was a Sasanian queen and royal consort, best known as the mother of the powerful fourth-century Sasanian king Shapur II.
-
C.
Hormazd
Hormazd is an alternative name for Ahura Mazda, the supreme creator god and central deity of Zoroastrianism.
-
D.
Bardiya
Bardiya was a son of the Achaemenid ruler Cyrus the Great who briefly and controversially claimed the Persian throne in the late 6th century BCE.
-
E.
Farhad
Farhad is a legendary tragic lover and sculptor in Persian literature, best known for his unrequited love and heroic labors in the romance of Khosrow and Shirin.
- 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_69d8e521855c8190b41871700afc8d6a |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e659cd4500819090363a4b7d6bf193 |
completed | April 20, 2026, 4:52 p.m. |
Created at: April 10, 2026, 1:53 p.m.