Triple
T23092286
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hagai Levi |
E575790
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Hagai |
—
|
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: Hagai | Statement: [Hagai Levi, givenName, Hagai]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hagai Context triple: [Hagai Levi, givenName, Hagai]
-
A.
Haggai
chosen
Haggai was a Hebrew prophet of the late 6th century BCE, known for urging the returned Jewish exiles to rebuild the Temple in Jerusalem.
-
B.
Ezra
Ezra is a prominent Jewish scribe and priest traditionally credited with leading religious reforms and restoring the Torah’s authority among the Israelites after the Babylonian exile.
-
C.
Ezra
Ezra is the mysterious and charismatic drifter who becomes entangled in the life of a young boy and his mother in the 2023 sci-fi drama film "Prospect," portrayed by Pedro Pascal.
-
D.
Ezra
Ezra is a mysterious, soft-spoken child who accompanies the protagonists in the surreal, narrative-driven adventure game Kentucky Route Zero.
-
E.
Nahum the Elkoshite
Nahum the Elkoshite is a Hebrew prophet known from the Old Testament for his oracle proclaiming the downfall of the Assyrian city of Nineveh.
- 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_69e245bf3e3c819086d3448720efc01b |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f18dab3798819081b2b46a20751b2a |
completed | April 29, 2026, 4:48 a.m. |
Created at: April 17, 2026, 3:57 p.m.