Triple
T21149180
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hank Azaria |
E521138
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object | Hal Azaria |
—
|
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: Hal Azaria | Statement: [Hank Azaria, child, Hal Azaria]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hal Azaria Context triple: [Hank Azaria, child, Hal Azaria]
-
A.
Hal Azaria
chosen
Hal Azaria is a child of American actor and voice artist Hank Azaria.
-
B.
Dov Karmi
Dov Karmi was a prominent Israeli architect known for helping shape the modernist architectural landscape of Tel Aviv and other parts of Israel in the mid-20th century.
-
C.
Eitan Berglas
Eitan Berglas was a prominent Israeli economist and academic leader known for his influential research in public finance and his role in shaping Israel’s economic policy and higher education.
-
D.
Shye Ben Tzur
Shye Ben Tzur is an Israeli composer, singer, and producer known for his fusion of Indian classical, Sufi, and Middle Eastern music, often performed in Hebrew, Urdu, and Hindi.
-
E.
Yigal Heller
Yigal Heller is an individual notable enough to be recognized as a prominent bearer of the surname Heller.
- 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_69e0b50c6a848190a4e525a77a319b8a |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e723ffb578819080a000987459a8a5 |
completed | April 21, 2026, 7:15 a.m. |
Created at: April 16, 2026, 2:58 p.m.