Triple
T21423448
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Spellbreaker |
E528493
|
entity |
| Predicate | engine |
P6068
|
FINISHED |
| Object | Z-machine |
—
|
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: Z-machine | Statement: [Spellbreaker, engine, Z-machine]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Z-machine Context triple: [Spellbreaker, engine, Z-machine]
-
A.
Z-machine
chosen
The Z-machine is a virtual machine designed to run Infocom's text adventure games across multiple computer platforms.
-
B.
Frotz
Frotz is a widely used open-source interpreter that runs interactive fiction games written for the Infocom Z-machine virtual machine.
-
C.
Harlowe
Harlowe is a small rural community located within the township of Addington Highlands in eastern Ontario, Canada.
-
D.
Zork
Zork is a pioneering text-based adventure video game series known for its rich interactive fiction, challenging puzzles, and influential role in early computer gaming.
-
E.
Oberon-2
Oberon-2 is an object-oriented, statically typed programming language that extends Niklaus Wirth’s Oberon with features like type-bound procedures and read-only export while preserving simplicity and efficiency.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0c455f3688190810bc96365791b0f |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ee8139ce848190b812d6d07f1bdef8 |
completed | April 26, 2026, 9:18 p.m. |
Created at: April 16, 2026, 5:48 p.m.