Triple
T37509003
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dausegne, the Fallen Oracle |
E932168
|
entity |
| Predicate | requiresGroupSize |
P176615
|
FINISHED |
| Object | 10-30 players |
—
|
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: 10-30 players | Statement: [Dausegne, the Fallen Oracle, requiresGroupSize, 10-30 players]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: requiresGroupSize Context triple: [Dausegne, the Fallen Oracle, requiresGroupSize, 10-30 players]
-
A.
sizeOfGroup
Indicates the number of individuals or elements that make up a particular group.
-
B.
requiresGroupContent
Indicates that an entity depends on or mandates the presence of content associated with a specific group in order to be valid, complete, or functional.
-
C.
sizeRequired
chosen
Indicates that a particular size or dimension is needed or must be met for something to be suitable, valid, or functional.
-
D.
typicalGroupSize
Indicates the usual or characteristic number of individuals that typically form a group in this context.
-
E.
numberOfGroup
Indicates the total count of groups associated with or contained by a given entity.
- 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_69f76ec5268481909ea01c73aeeefd42 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a0064f8efa48190956287f548a8057d |
completed | May 10, 2026, 10:59 a.m. |
| PD | Predicate disambiguation | batch_6a006471e75c8190adae99bd75e7411b |
completed | May 10, 2026, 10:56 a.m. |
Created at: May 3, 2026, 4:17 p.m.