Triple
T14159835
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Epistulae |
E350906
|
entity |
| Predicate | containsFamousLetterAbout |
P17387
|
FINISHED |
| Object | eruption of Mount Vesuvius in AD 79 |
—
|
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: eruption of Mount Vesuvius in AD 79 | Statement: [Epistulae, containsFamousLetterAbout, eruption of Mount Vesuvius in AD 79]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: containsFamousLetterAbout Context triple: [Epistulae, containsFamousLetterAbout, eruption of Mount Vesuvius in AD 79]
-
A.
hasLetterBy
Indicates that an entity possesses or is associated with a letter authored or sent by another entity.
-
B.
hasLetter
chosen
Indicates that one entity contains, includes, or is associated with a specific letter or character.
-
C.
hasLettersFor
Indicates that one entity possesses or contains written correspondence intended for another entity.
-
D.
usesAdditionalLettersFrom
Indicates that one entity forms or derives its representation by incorporating extra letters taken from another entity beyond those originally present.
-
E.
hasNotablePersonWithSurname
Indicates that an entity is associated with at least one notable person who bears a specified surname.
- 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_69d8278775fc8190b0802d22ca2f495d |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de61393f308190bb357e2bd1916f94 |
completed | April 14, 2026, 3:46 p.m. |
| PD | Predicate disambiguation | batch_69de05b8434c81908c33b1b513463b12 |
completed | April 14, 2026, 9:15 a.m. |
Created at: April 10, 2026, 12:58 a.m.