Triple
T19645581
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thunderstone |
E471662
|
entity |
| Predicate | hasMember |
P10
|
FINISHED |
| Object |
Kari Tornack
Kari Tornack is a character from the Thunderstone deck-building game, typically depicted as a powerful hero used to battle monsters in the dungeon.
|
E1391473
|
NE FINISHED |
How this triple was built (4 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: Kari Tornack | Statement: [Thunderstone, hasMember, Kari Tornack]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kari Tornack Context triple: [Thunderstone, hasMember, Kari Tornack]
-
A.
Kara Nortman
Kara Nortman is a technology investor and entrepreneur best known as a co-founder and co-owner of the National Women's Soccer League club Angel City FC.
-
B.
Kari Skogland
Kari Skogland is a Canadian film and television director, producer, and screenwriter known for her work on acclaimed series such as The Handmaid’s Tale and The Falcon and the Winter Soldier.
-
C.
Kay Tornborg
Kay Tornborg is an American artist and the former wife of actor Christopher Lloyd.
-
D.
Kari Holbrook
Kari Holbrook is an individual notable enough to be recognized as a prominent bearer of the Holbrook surname.
-
E.
Carlene Olson
Carlene Olson is an American actress and former model best known for her marriage to actor Michael Biehn.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Kari Tornack Triple: [Thunderstone, hasMember, Kari Tornack]
Generated description
Kari Tornack is a character from the Thunderstone deck-building game, typically depicted as a powerful hero used to battle monsters in the dungeon.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Kari Tornack Target entity description: Kari Tornack is a character from the Thunderstone deck-building game, typically depicted as a powerful hero used to battle monsters in the dungeon.
-
A.
Kara Nortman
Kara Nortman is a technology investor and entrepreneur best known as a co-founder and co-owner of the National Women's Soccer League club Angel City FC.
-
B.
Kari Skogland
Kari Skogland is a Canadian film and television director, producer, and screenwriter known for her work on acclaimed series such as The Handmaid’s Tale and The Falcon and the Winter Soldier.
-
C.
Kay Tornborg
Kay Tornborg is an American artist and the former wife of actor Christopher Lloyd.
-
D.
Kari Holbrook
Kari Holbrook is an individual notable enough to be recognized as a prominent bearer of the Holbrook surname.
-
E.
Carlene Olson
Carlene Olson is an American actress and former model best known for her marriage to actor Michael Biehn.
- F. None of above. chosen
Provenance (5 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_69d8e51395348190ac1416d46dfc6db0 |
completed | April 10, 2026, 11:54 a.m. |
| NER | Named-entity recognition | batch_69e641250e108190a707452fefc87041 |
completed | April 20, 2026, 3:07 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a07ab86569481908bd219fd45561bac |
completed | May 15, 2026, 11:25 p.m. |
| NEDg | Description generation | batch_6a07ae93da48819093a314ced1fbeb6b |
completed | May 15, 2026, 11:39 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a07af04839c8190aadbc4320854b619 |
completed | May 15, 2026, 11:40 p.m. |
Created at: April 10, 2026, 1:44 p.m.