Triple
T8395841
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hogwarts Mystery |
E198049
|
entity |
| Predicate | publisher |
P29
|
FINISHED |
| Object | Jam City |
E730469
|
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: Jam City | Statement: [Hogwarts Mystery, publisher, Jam City]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jam City Context triple: [Hogwarts Mystery, publisher, Jam City]
-
A.
Jam City
chosen
Jam City is a mobile game development studio known for creating popular free-to-play titles, including the Harry Potter: Hogwarts Mystery game.
-
B.
Block City
Block City is a compact, block-themed battle arena course featured in the multiplayer Battle Mode of Mario Kart: Double Dash!!.
-
C.
Jump City
Jump City is a fictional, crime-ridden coastal metropolis in the DC Comics universe that serves as the home base and primary battleground for the Teen Titans.
-
D.
Sand City
Sand City is a small coastal city in Monterey County, California, known for its beaches, sand dunes, and outlet shopping.
-
E.
Apple City
Apple City is a nickname for Daegu, a major South Korean city historically renowned for its abundant apple production.
- 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_69ca82f816bc8190ab321c07d72208c1 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb81874d6c8190bbc0ac832d8a339d |
completed | March 31, 2026, 8:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ce02d5e0648190b33011c2ddca4ad3 |
completed | April 2, 2026, 5:47 a.m. |
Created at: March 30, 2026, 6:04 p.m.