Triple
T16577022
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Doctor Who series 5 |
E402737
|
entity |
| Predicate | episode |
P53537
|
FINISHED |
| Object | Cold Blood |
E733528
|
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: Cold Blood | Statement: [Doctor Who series 5, episode, Cold Blood]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cold Blood Context triple: [Doctor Who series 5, episode, Cold Blood]
-
A.
Cold Blood
chosen
Cold Blood is a British crime drama television series in which John Hannah stars as a convicted killer assisting the police with investigations.
-
B.
Cold Blooded
"Cold Blooded" is a song by the American rapper Poison, known for its hard-edged style and dark, aggressive themes.
-
C.
Cold Blooded
"Cold Blooded" is a 1983 funk and R&B hit single by Rick James, known for its synth-driven groove and distinctive vocal style.
-
D.
Cold Blooded
"Cold Blooded" is a chapter or section within the novel "Like Water for Chocolate," contributing to its blend of magical realism, romance, and culinary tradition.
-
E.
Born to Kill
Born to Kill is a 1947 American film noir crime drama known for its dark, violent storyline and morally corrupt characters.
- 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_69d88387363c8190a97a0c942130de97 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e3595dd90881909933216bd12505e1 |
completed | April 18, 2026, 10:13 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a006eecbb6c81908abc5659333a4879 |
completed | May 10, 2026, 11:41 a.m. |
Created at: April 10, 2026, 5:16 a.m.