Triple
T37515798
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Runic Games |
E932629
|
entity |
| Predicate | developedFranchise |
P71535
|
FINISHED |
| Object | Torchlight |
—
|
NE NERFINISHED |
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: Torchlight | Statement: [Runic Games, developedFranchise, Torchlight]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: developedFranchise Context triple: [Runic Games, developedFranchise, Torchlight]
-
A.
gameFranchise
Indicates that one entity is a video game franchise to which the other entity (such as a specific game, character, or related media) belongs or is associated.
-
B.
franchiseUniverse
Indicates that multiple works, characters, or stories exist within and are connected by the same overarching fictional franchise or narrative universe.
-
C.
developedSeries
Indicates that one entity is responsible for creating or developing a particular series associated with the other entity.
-
D.
franchiseWorkedOn
Indicates that an entity has contributed work to, or been professionally involved with, a particular franchise.
-
E.
studioFranchise
chosen
Indicates that a studio is associated with, produces, or manages a particular franchise.
- F. None of above.
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_69f76ec730988190b5aa4f9cb9afd518 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fdee770af48190aca2670db50f8b49 |
completed | May 8, 2026, 2:08 p.m. |
| PD | Predicate disambiguation | batch_69fdecec98a08190a357d816dc2a6dbe |
completed | May 8, 2026, 2:02 p.m. |
Created at: May 3, 2026, 4:17 p.m.