Triple
T37457112
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Freeze Mage |
E930826
|
entity |
| Predicate | roleInMeta |
P203798
|
FINISHED |
| Object | control-combo counter to slow decks |
—
|
LITERAL 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: control-combo counter to slow decks | Statement: [Freeze Mage, roleInMeta, control-combo counter to slow decks]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleInMeta Context triple: [Freeze Mage, roleInMeta, control-combo counter to slow decks]
-
A.
roleInMetadata
Indicates that an entity serves a specific function or position within a metadata record or metadata structure.
-
B.
roleInText
Indicates that an entity participates in a text with a specific function or capacity (e.g., author, editor, character).
-
C.
roleInMATE
Indicates that an entity participates in a MATE (Modeling and Analysis of Telecommunication Systems) context with a specific functional or contextual role.
-
D.
roleInName
Indicates that a specific role, title, or position is included as part of an entity’s name or naming expression.
-
E.
roleAtAnthropic
Indicates that an entity holds or held a specific role or position at Anthropic.
- F. None of above. chosen
Provenance (4 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_69f76ec1a1148190b0a961f188d621b0 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a0205c0bff481908238a382459b3a93 |
completed | May 11, 2026, 4:37 p.m. |
| PD | Predicate disambiguation | batch_6a0205143f20819087ee31576835be26 |
completed | May 11, 2026, 4:34 p.m. |
| PDg | Predicate description generation | batch_6a0205bfab208190982728a690ce183d |
completed | May 11, 2026, 4:37 p.m. |
Created at: May 3, 2026, 4:17 p.m.