Triple
T1105189
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Accused |
E25472
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object | Tom Topor |
E125458
|
NE FINISHED |
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: Tom Topor | Statement: [The Accused, screenwriter, Tom Topor]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tom Topor Context triple: [The Accused, screenwriter, Tom Topor]
-
A.
Tom Topor
chosen
Tom Topor is an American screenwriter and playwright best known for his work on the acclaimed courtroom drama film "The Accused."
-
B.
Edward Szczepanik
Edward Szczepanik was a Polish economist and politician who served as the last prime minister of the Polish government-in-exile before the restoration of democracy in Poland.
-
C.
Daniel Tarschys
Daniel Tarschys is a Swedish political scientist and politician who served as Secretary General of the Council of Europe in the 1990s.
-
D.
Tony Kubek
Tony Kubek is a former Major League Baseball shortstop and longtime television broadcaster best known for his work as a color commentator on national baseball telecasts.
-
E.
Leo Tover
Leo Tover was an American cinematographer known for his work on numerous classic Hollywood films across several decades.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69a49428d4448190b3b36991ceae87ce |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4b9e21f048190bf4b63dd2c7c7641 |
completed | March 1, 2026, 10:12 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ac5391a4a88190b7ef6993b2b85b08 |
completed | March 7, 2026, 4:34 p.m. |
Created at: March 1, 2026, 7:43 p.m.