Triple
T23317591
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Miranda Raison |
E590751
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Warrior Queen |
—
|
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: Warrior Queen | Statement: [Miranda Raison, notableWork, Warrior Queen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Warrior Queen Context triple: [Miranda Raison, notableWork, Warrior Queen]
-
A.
Warrior Queen
chosen
Warrior Queen is a 2003 historical drama film depicting the life and rebellion of the ancient British Iceni queen Boudica against Roman rule.
-
B.
Barbarian Queen
Barbarian Queen is a 1985 low-budget fantasy adventure film known for its sword-and-sorcery themes and for starring Lana Clarkson as a vengeful warrior.
-
C.
Warrior Woman
Warrior Woman is a formidable female combatant renowned for fiercely opposing invading forces.
-
D.
Shadow Queen
The Shadow Queen is an ancient, malevolent demon and final boss in Paper Mario: The Thousand-Year Door who seeks to engulf the world in darkness.
-
E.
Guerrière
Guerrière was a French warship that took part in the decisive 1827 naval Battle of Navarino during the Greek War of Independence.
- 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_69e25d1d32188190948eb76909d1dcc3 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f197828c408190ae071624e40de4cc |
completed | April 29, 2026, 5:30 a.m. |
Created at: April 17, 2026, 5:06 p.m.