Triple
T7628466
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ozma of Oz |
E172696
|
entity |
| Predicate | hasAntagonist |
P18963
|
FINISHED |
| Object | Nome King |
E161152
|
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: Nome King | Statement: [Ozma of Oz, hasAntagonist, Nome King]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nome King Context triple: [Ozma of Oz, hasAntagonist, Nome King]
-
A.
Nome King
chosen
The Nome King is a powerful and malevolent ruler of the underground Nomes in L. Frank Baum’s Oz series, known for his antagonism toward the Emerald City and its inhabitants.
-
B.
King
King is a British Christian rock and worship band known for its energetic live performances and faith-centered lyrics.
-
C.
King
The King of Norway is the constitutional monarch and ceremonial head of state in Norway’s parliamentary system.
-
D.
King
King is a prominent video game company best known for creating the massively popular mobile puzzle game Candy Crush Saga.
-
E.
King
King is a regal title traditionally denoting a male sovereign ruler of a kingdom, often associated with supreme authority and hereditary monarchy.
- 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_69c699517e348190bd3348b6889200f2 |
completed | March 27, 2026, 2:50 p.m. |
| NER | Named-entity recognition | batch_69c6fa831f508190ab2f72326cdf4497 |
completed | March 27, 2026, 9:45 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c870af222481909e341eebb78664d6 |
completed | March 29, 2026, 12:22 a.m. |
Created at: March 27, 2026, 3:56 p.m.