Triple
T11669331
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thin Man |
E277336
|
entity |
| Predicate | publisher |
P29
|
FINISHED |
| Object | 2K Games |
E388069
|
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: 2K Games | Statement: [Thin Man, publisher, 2K Games]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 2K Games Context triple: [Thin Man, publisher, 2K Games]
-
A.
2K Games
chosen
2K Games is a major American video game publisher known for franchises such as NBA 2K, BioShock, Borderlands, and Civilization.
-
B.
2K Play
2K Play is a publishing label of 2K focused on casual, family-friendly, and licensed video games.
-
C.
Take-Two Interactive
Take-Two Interactive is a major American video game publisher known for franchises like Grand Theft Auto, Red Dead Redemption, and NBA 2K.
-
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.
Midway Games
Midway Games was an American video game company best known for publishing and developing popular arcade and console titles such as the Mortal Kombat series.
- 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_69d6aafd0a448190b44da30af8c6c519 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a440d8a481909a13c97813408bc8 |
completed | April 10, 2026, 7:18 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ef13c3ea648190ae18cd2869be74ad |
completed | April 27, 2026, 7:44 a.m. |
Created at: April 8, 2026, 9:39 p.m.