Triple
T3292194
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Red Dust |
E69126
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object | Troy Kennedy Martin |
E250955
|
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: Troy Kennedy Martin | Statement: [Red Dust, screenwriter, Troy Kennedy Martin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Troy Kennedy Martin Context triple: [Red Dust, screenwriter, Troy Kennedy Martin]
-
A.
Troy Kennedy Martin
chosen
Troy Kennedy Martin was a British television and film screenwriter best known for creating the series "Z-Cars" and writing the original 1969 film "The Italian Job."
-
B.
Henry Bowers
Henry Bowers is a sadistic teenage bully and one of the primary human antagonists in the 2017 horror film adaptation of Stephen King’s "It."
-
C.
Thomas Matthew
Thomas Matthew is the pseudonym of John Rogers, the 16th-century English Protestant who compiled and published the influential Matthew Bible translation.
-
D.
Christopher Wallace
Christopher Wallace is an American journalist and television news anchor known for his incisive political interviews and long career at major U.S. networks.
-
E.
Joe Danelo
Joe Danelo is a former NFL placekicker best known for his tenure with the New York Giants in the late 1970s and early 1980s.
- 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_69ad859d45748190b0742408c954b39f |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb07379dc8190b7bb409bcf42bdd6 |
completed | March 8, 2026, 5:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b2e86895988190a7acaa5948b50bcd |
completed | March 12, 2026, 4:23 p.m. |
Created at: March 8, 2026, 3:10 p.m.