Triple
T7785498
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shanté Smith |
E187231
|
entity |
| Predicate | adversaryOf |
P18963
|
FINISHED |
| Object |
Conny Spalding
Conny Spalding is a character in the film "Two Can Play That Game," serving as a romantic rival and source of conflict for the protagonist Shanté Smith.
|
E692729
|
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: Conny Spalding | Statement: [Shanté Smith, adversaryOf, Conny Spalding]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Conny Spalding Context triple: [Shanté Smith, adversaryOf, Conny Spalding]
-
A.
Connie Palmen
Connie Palmen is a Dutch novelist and essayist known for her psychologically rich, intellectually layered works that explore identity, relationships, and authorship.
-
B.
Toni Körner
Toni Körner is a person notable enough to be recognized as a prominent bearer of the surname Körner.
-
C.
Linda Spalding
Linda Spalding is a Canadian-American writer and editor known for her award-winning fiction and non-fiction, including works that explore history, identity, and moral complexity.
-
D.
Conny
Conny is a common diminutive or nickname for the given name Cornelia.
-
E.
Marlene Knaus
Marlene Knaus is an Austrian former model best known as the ex-wife of Formula One legend Niki Lauda.
- 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: Conny Spalding Triple: [Shanté Smith, adversaryOf, Conny Spalding]
Generated description
Conny Spalding is a character in the film "Two Can Play That Game," serving as a romantic rival and source of conflict for the protagonist Shanté Smith.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Conny Spalding Target entity description: Conny Spalding is a character in the film "Two Can Play That Game," serving as a romantic rival and source of conflict for the protagonist Shanté Smith.
-
A.
Connie Palmen
Connie Palmen is a Dutch novelist and essayist known for her psychologically rich, intellectually layered works that explore identity, relationships, and authorship.
-
B.
Toni Körner
Toni Körner is a person notable enough to be recognized as a prominent bearer of the surname Körner.
-
C.
Linda Spalding
Linda Spalding is a Canadian-American writer and editor known for her award-winning fiction and non-fiction, including works that explore history, identity, and moral complexity.
-
D.
Conny
Conny is a common diminutive or nickname for the given name Cornelia.
-
E.
Marlene Knaus
Marlene Knaus is an Austrian former model best known as the ex-wife of Formula One legend Niki Lauda.
- 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_69ca82af2d2c8190963861f5e0b8bf21 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cadf22d9b4819081b877c751204a22 |
completed | March 30, 2026, 8:37 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69caf604715081909eed614cbadb8db6 |
completed | March 30, 2026, 10:15 p.m. |
| NEDg | Description generation | batch_69caf81ff934819094f8089b0bd8dde7 |
completed | March 30, 2026, 10:24 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69cafa512e748190a52fe462d3d59f06 |
completed | March 30, 2026, 10:33 p.m. |
Created at: March 30, 2026, 4:23 p.m.