Triple
T22973908
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Broken City |
E571260
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Alona Tal |
—
|
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: Alona Tal | Statement: [Broken City, starring, Alona Tal]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Alona Tal Context triple: [Broken City, starring, Alona Tal]
-
A.
Alona Tal
chosen
Alona Tal is an Israeli-American actress and singer known for her roles in television series such as "Veronica Mars," "Supernatural," and "Hand of God."
-
B.
Daliah Lavi
Daliah Lavi was an Israeli actress, singer, and model best known internationally for her roles in 1960s European and Hollywood films, particularly in stylish spy spoofs and adventure movies.
-
C.
Tamar Shalev
Tamar Shalev is known as the wife of the late Israeli author and columnist Meir Shalev.
-
D.
Saar Ganor
Saar Ganor is an Israeli archaeologist known for directing major excavations at key biblical-era sites, including the fortified city of Tel Qeiyafa.
-
E.
Meital Berdah
Meital Berdah is an Israeli actress known for her work in film and television and for being married to actor and "Fauda" co-creator Lior Raz.
- 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_69e245b2c6548190a0e4c7f2f7df2d48 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f182350b448190a34e5fa0167fd964 |
completed | April 29, 2026, 3:59 a.m. |
Created at: April 17, 2026, 3:48 p.m.