Triple
T3778356
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2K |
E83360
|
entity |
| Predicate | hasDivision |
P35
|
FINISHED |
| Object |
2K Sports
2K Sports is a video game publishing label best known for its popular sports simulation franchises such as NBA 2K.
|
E388069
|
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: 2K Sports | Statement: [2K, hasDivision, 2K Sports]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 2K Sports Context triple: [2K, hasDivision, 2K Sports]
-
A.
EA Sports
EA Sports is a video game brand of Electronic Arts best known for developing popular sports game franchises such as FIFA (now EA Sports FC) and Madden NFL.
-
B.
2K Games
2K Games is a major American video game publisher known for franchises such as NBA 2K, BioShock, Borderlands, and Civilization.
-
C.
Electronic Arts
Electronic Arts is a major American video game company best known for publishing popular franchises such as FIFA, Madden NFL, Battlefield, and The Sims.
-
D.
Activision Blizzard
Activision Blizzard is a major American video game holding company known for franchises such as Call of Duty, World of Warcraft, and Overwatch.
-
E.
Activision Publishing
Activision Publishing is a major American video game publisher best known for franchises like Call of Duty, Crash Bandicoot, and Tony Hawk’s Pro Skater.
- 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: 2K Sports Triple: [2K, hasDivision, 2K Sports]
Generated description
2K Sports is a video game publishing label best known for its popular sports simulation franchises such as NBA 2K.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: 2K Sports Target entity description: 2K Sports is a video game publishing label best known for its popular sports simulation franchises such as NBA 2K.
-
A.
EA Sports
EA Sports is a video game brand of Electronic Arts best known for developing popular sports game franchises such as FIFA (now EA Sports FC) and Madden NFL.
-
B.
2K Games
chosen
2K Games is a major American video game publisher known for franchises such as NBA 2K, BioShock, Borderlands, and Civilization.
-
C.
Electronic Arts
Electronic Arts is a major American video game company best known for publishing popular franchises such as FIFA, Madden NFL, Battlefield, and The Sims.
-
D.
Activision Blizzard
Activision Blizzard is a major American video game holding company known for franchises such as Call of Duty, World of Warcraft, and Overwatch.
-
E.
Activision Publishing
Activision Publishing is a major American video game publisher best known for franchises like Call of Duty, Crash Bandicoot, and Tony Hawk’s Pro Skater.
- F. None of above.
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_69ad8b235e608190b5a2b1d1bfcef50b |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69adcc78173081908b230017834cdf9e |
completed | March 8, 2026, 7:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b54c2971788190b8f48da3883d2ba2 |
completed | March 14, 2026, 11:53 a.m. |
| NEDg | Description generation | batch_69b55004ef54819090a714478a8ff6e8 |
completed | March 14, 2026, 12:09 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69b5508ab77c819080cd8a87818ea482 |
completed | March 14, 2026, 12:11 p.m. |
Created at: March 8, 2026, 3:36 p.m.