Triple
T38589270
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Frozen Throne |
E932415
|
entity |
| Predicate | laterLichKing |
P203436
|
FINISHED |
| Object | Arthas Menethil |
—
|
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: Arthas Menethil | Statement: [The Frozen Throne, laterLichKing, Arthas Menethil]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: laterLichKing Context triple: [The Frozen Throne, laterLichKing, Arthas Menethil]
-
A.
formerWarchief
Indicates that one entity previously held the role or title of warchief over another entity but no longer does.
-
B.
statusAfterWrathOfTheLichKing
Indicates the state or condition of an entity following the events or timeframe associated with the Wrath of the Lich King.
-
C.
lastKingBeforeStewards
Indicates that one entity is the final king who ruled immediately prior to the period when stewards assumed governing authority over the other entity.
-
D.
outcomeForWitchKing
Indicates the resulting fate, consequence, or end state that befalls the Witch King.
-
E.
lastKnightAppointed
Indicates that a particular knight is the most recently appointed knight in a given context or order.
- F. None of above. chosen
Provenance (4 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_69f76ec654d48190b421111cf26e54d9 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a017d27e184819094638c3cf6876de4 |
completed | May 11, 2026, 6:54 a.m. |
| PD | Predicate disambiguation | batch_6a017c785a44819083111384b55769e9 |
completed | May 11, 2026, 6:51 a.m. |
| PDg | Predicate description generation | batch_6a017d270e9881909e70280ff4e45e9a |
completed | May 11, 2026, 6:54 a.m. |
Created at: May 3, 2026, 4:32 p.m.