Triple
T14800539
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hardhome |
E347898
|
entity |
| Predicate | featuresCharacter |
P626
|
FINISHED |
| Object | Wun Wun |
E1116159
|
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: Wun Wun | Statement: [Hardhome, featuresCharacter, Wun Wun]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Wun Wun Context triple: [Hardhome, featuresCharacter, Wun Wun]
-
A.
Wun Wun
chosen
Wun Wun is a giant allied with Jon Snow in Game of Thrones, known for his immense strength and pivotal role in key battles.
-
B.
Wunna
Wunna is a studio album by American rapper Gunna that helped solidify his mainstream success with its melodic trap sound and chart-topping performance.
-
C.
Wazhazhe
Wazhazhe is the self-designation of the Osage people, a Native American nation originally from the central United States.
-
D.
Wondunna
Wondunna is a residential suburb located within the coastal city of Hervey Bay in Queensland, Australia.
-
E.
Wee Waa
Wee Waa is a small rural town in north-western New South Wales, Australia, known historically as an important cotton-growing and agricultural centre.
- 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_69d822ea8b7c819097dfadf3d45545e6 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69decd62c36c81909c2993dc7d1a79ea |
completed | April 14, 2026, 11:27 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe24c4f690819087504fcfd2df8ba3 |
completed | May 8, 2026, 6 p.m. |
Created at: April 10, 2026, 1:31 a.m.