Triple
T16000075
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2K Games |
E388069
|
entity |
| Predicate | division |
P889
|
FINISHED |
| Object |
Hangar 13
Hangar 13 is a video game development studio best known for creating titles in the Mafia series under publisher 2K Games.
|
E1187804
|
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: Hangar 13 | Statement: [2K Games, division, Hangar 13]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hangar 13 Context triple: [2K Games, division, Hangar 13]
-
A.
Hangar 18
"Hangar 18" is a popular thrash metal song by Megadeth, known for its intricate guitar work and lyrics about government cover-ups of extraterrestrial life.
-
B.
Mortlock Wing
The Mortlock Wing is a historic Victorian-era library building in Adelaide renowned for its ornate architecture and role as a prominent cultural landmark within the State Library of South Australia.
-
C.
U.S. Outpost 31
U.S. Outpost 31 is the remote Antarctic research station that serves as the primary setting for John Carpenter’s 1982 horror film "The Thing."
-
D.
Corridor X
Corridor X is a major pan-European transport route that connects Central Europe with Greece’s Aegean coast, facilitating regional trade and transit through the Balkans.
-
E.
Lethal Orbit
Lethal Orbit is a film featuring actress Carrie Mitchum in a prominent role.
- 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: Hangar 13 Triple: [2K Games, division, Hangar 13]
Generated description
Hangar 13 is a video game development studio best known for creating titles in the Mafia series under publisher 2K Games.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Hangar 13 Target entity description: Hangar 13 is a video game development studio best known for creating titles in the Mafia series under publisher 2K Games.
-
A.
Hangar 18
"Hangar 18" is a popular thrash metal song by Megadeth, known for its intricate guitar work and lyrics about government cover-ups of extraterrestrial life.
-
B.
Mortlock Wing
The Mortlock Wing is a historic Victorian-era library building in Adelaide renowned for its ornate architecture and role as a prominent cultural landmark within the State Library of South Australia.
-
C.
U.S. Outpost 31
U.S. Outpost 31 is the remote Antarctic research station that serves as the primary setting for John Carpenter’s 1982 horror film "The Thing."
-
D.
Corridor X
Corridor X is a major pan-European transport route that connects Central Europe with Greece’s Aegean coast, facilitating regional trade and transit through the Balkans.
-
E.
Lethal Orbit
Lethal Orbit is a film featuring actress Carrie Mitchum in a prominent role.
- 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_69d86daa562c81908aacc179c0fe8fb5 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e1578a0adc819097c6a23514182173 |
completed | April 16, 2026, 9:41 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffc3d99ca08190a3d07a0802b1b24a |
completed | May 9, 2026, 11:31 p.m. |
| NEDg | Description generation | batch_69ffc44e8b0c81909b8af9006aa5fc4d |
completed | May 9, 2026, 11:33 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69ffc4bdf840819085e0a537e126c704 |
completed | May 9, 2026, 11:35 p.m. |
Created at: April 10, 2026, 4:55 a.m.