Triple
T14466213
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Poems on Several Occasions |
E358714
|
entity |
| Predicate | hasWikidataEntity |
P31855
|
FINISHED |
| Object | Q7226891 |
—
|
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: Q7226891 | Statement: [Poems on Several Occasions, hasWikidataEntity, Q7226891]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasWikidataEntity Context triple: [Poems on Several Occasions, hasWikidataEntity, Q7226891]
-
A.
hasWikidataItem
chosen
Indicates that an entity is associated with a specific corresponding item in the Wikidata knowledge base.
-
B.
hasWikidataProperty
Indicates that one entity is associated with a specific Wikidata property used to describe or qualify it.
-
C.
hasEnglishWikipediaArticle
Indicates that there exists an article about the subject in the English-language edition of Wikipedia.
-
D.
hasWikipediaLanguageEdition
Indicates that a particular language has its own dedicated edition of Wikipedia available in that language.
-
E.
hasLanguageCodeOnWikipedia
Indicates that a particular language is represented on Wikipedia by a specific language code.
- 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_69d827966698819082e140837737501d |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de91f6d4c08190a12e9a5901ee3508 |
completed | April 14, 2026, 7:13 p.m. |
| PD | Predicate disambiguation | batch_69de5c42bd3c81909a62acf30cc24d1e |
completed | April 14, 2026, 3:24 p.m. |
Created at: April 10, 2026, 1:19 a.m.