Triple
T9550832
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lawrence Mark Sanger |
E230416
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Citizendium |
E219661
|
NE 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: Citizendium | Statement: [Lawrence Mark Sanger, notableWork, Citizendium]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Citizendium Context triple: [Lawrence Mark Sanger, notableWork, Citizendium]
-
A.
Citizendium
chosen
Citizendium is an expert-guided, wiki-based online encyclopedia project founded as an alternative to Wikipedia, emphasizing real-name authorship and expert oversight.
-
B.
Wikipedia
Wikipedia is a free, collaboratively edited online encyclopedia that allows users worldwide to create and modify its articles.
-
C.
Nupedia
Nupedia was an early online encyclopedia project known for its expert-written, peer-reviewed articles and for serving as the precursor to Wikipedia.
-
D.
Wikisource
Wikisource is a free online digital library of public domain and freely licensed texts that anyone can read and help transcribe.
-
E.
Portalis
Portalis is a French surname most notably associated with Jean-Étienne-Marie Portalis, a principal drafter of the Napoleonic Civil Code.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca847d3be8819099c9dad2a7e786f1 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd991df7308190a56d95f195627513 |
completed | April 1, 2026, 10:15 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d14c85b9208190acf98fa985b0f01f |
completed | April 4, 2026, 5:38 p.m. |
Created at: March 30, 2026, 8:02 p.m.