Triple
T7191369
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael Winner |
E167698
|
entity |
| Predicate | directed |
P7373
|
FINISHED |
| Object | Scorpio |
E646698
|
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: Scorpio | Statement: [Michael Winner, directed, Scorpio]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Scorpio Context triple: [Michael Winner, directed, Scorpio]
-
A.
Scorpio
chosen
"Scorpio" is a 1973 Cold War spy thriller film directed by Michael Winner, starring Burt Lancaster and Alain Delon as rival assassins entangled in CIA intrigue.
-
B.
Scorpio
Scorpio is the intense and mysterious eighth sign of the zodiac, associated with passion, transformation, and emotional depth.
-
C.
Skorpios
Skorpios is a privately owned Greek island in the Ionian Sea, famously associated with Aristotle Onassis and his family.
-
D.
Capricorn
Capricorn is an earth sign in astrology known for its ambition, discipline, and practical, goal-oriented nature.
-
E.
Capricorn
Capricorn is the ruthless and sadistic villain in Cornelia Funke’s fantasy novel "Inkheart," known for being read out of a book into the real world and terrorizing others with his band of henchmen.
- 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_69c6888b5248819090499a884ee3ec39 |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6e90087208190a65e49ae0e8a7cbf |
completed | March 27, 2026, 8:30 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7bf95a1a0819099d252f037c318c7 |
completed | March 28, 2026, 11:46 a.m. |
Created at: March 27, 2026, 2:50 p.m.