Triple
T30300144
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dictionary (Swift) |
E770631
|
entity |
| Predicate | valueMultiplicity |
P83554
|
FINISHED |
| Object | values may be duplicated |
—
|
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: values may be duplicated | Statement: [Dictionary (Swift), valueMultiplicity, values may be duplicated]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: valueMultiplicity Context triple: [Dictionary (Swift), valueMultiplicity, values may be duplicated]
-
A.
multiplicity
Indicates the number of instances of one entity that can or must be associated with a single instance of another entity within a relationship.
-
B.
positionOnMultiplicity
Indicates that one entity’s position or placement is defined relative to multiple instances or occurrences of another entity.
-
C.
variantCount
Indicates the number of distinct variants associated with a given entity or item.
-
D.
multipleValuesAllowed
chosen
Indicates that the relationship or attribute can be associated with more than one value simultaneously, rather than being restricted to a single value.
-
E.
isSingleValuedOn
Indicates that for each element in the specified domain, the relation associates at most one corresponding value in the codomain.
- 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_69f224881b948190b8c4921b250a44a3 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f6abaa1f648190b77073771df3bf3b |
completed | May 3, 2026, 1:58 a.m. |
| PD | Predicate disambiguation | batch_69f6aa1e84b88190b025f6ca40f17a8a |
completed | May 3, 2026, 1:51 a.m. |
Created at: April 29, 2026, 7:48 p.m.