Triple
T20984436
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Midianite |
E516857
|
entity |
| Predicate | associatedWithFigure |
P1183
|
FINISHED |
| Object | Zipporah |
—
|
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: Zipporah | Statement: [Midianite, associatedWithFigure, Zipporah]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Zipporah Context triple: [Midianite, associatedWithFigure, Zipporah]
-
A.
Zipporah
chosen
Zipporah is the Midianite wife of Moses in the Hebrew Bible, known for accompanying him to Egypt and intervening to save his life in a mysterious incident involving their son’s circumcision.
-
B.
Zilpah
Zilpah is a biblical figure who served as Leah’s maidservant and bore two of Jacob’s sons, Gad and Asher.
-
C.
Miryam
Miryam is the Hebrew form of the name of the Virgin Mary, the mother of Jesus in Christian tradition.
-
D.
Miriam
Miriam "Midge" Maisel is the quick-witted 1950s New York housewife-turned-stand-up-comedian who stars as the protagonist of the television series "The Marvelous Mrs. Maisel."
-
E.
Miriam
Miriam is a fictional character from the British dark comedy television series "The Life and Times of Vivienne Vyle."
- 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_69e0b4ffac148190bbade9f0eceb660b |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6fbe1474c8190912b90da0973f99f |
completed | April 21, 2026, 4:24 a.m. |
Created at: April 16, 2026, 1:48 p.m.