Triple
T29106844
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Weiqi |
E736783
|
entity |
| Predicate | typicalKomiRange |
P13474
|
FINISHED |
| Object | 5.5 to 7.5 points in modern play |
—
|
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: 5.5 to 7.5 points in modern play | Statement: [Weiqi, typicalKomiRange, 5.5 to 7.5 points in modern play]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalKomiRange Context triple: [Weiqi, typicalKomiRange, 5.5 to 7.5 points in modern play]
-
A.
typicalRange
chosen
Indicates the usual or expected range of values, conditions, or states within which something normally occurs or applies.
-
B.
hasKomiRule
Indicates that a game or match is governed by a specific komi rule, defining the compensation points given to one player.
-
C.
typicalPegRange
Indicates the usual or standard range of peg values within which something is normally maintained or expected to operate.
-
D.
typicalRangeClass
Indicates that the related entity belongs to a class whose members typically fall within a characteristic or expected value range.
-
E.
typicalRangeMinimum_km
Indicates the minimum distance, in kilometers, that is typically observed or expected within a given range for the relationship or measurement in question.
- 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_69f077ec765c81909474c88bcc8bab43 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_6a017969ff908190a7a1a46b3f5ae362 |
completed | May 11, 2026, 6:38 a.m. |
| PD | Predicate disambiguation | batch_6a017609ff4c8190aba8a1864d39a608 |
completed | May 11, 2026, 6:24 a.m. |
Created at: April 28, 2026, 11:16 a.m.