Triple
T6935974
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lament for the Makaris |
E160554
|
entity |
| Predicate | usesLatinPhrase |
P9999
|
FINISHED |
| Object | Timor mortis conturbat me |
—
|
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: Timor mortis conturbat me | Statement: [Lament for the Makaris, usesLatinPhrase, Timor mortis conturbat me]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesLatinPhrase Context triple: [Lament for the Makaris, usesLatinPhrase, Timor mortis conturbat me]
-
A.
usesLatinAlphabetSince
Indicates that an entity has employed the Latin alphabet as its writing system starting from a specific point in time and continuing thereafter.
-
B.
correspondsToLatinWord
Indicates that one element is the equivalent or matching term of another element in Latin.
-
C.
hasLatinName
Indicates that an entity is associated with a specific Latin (scientific) name.
-
D.
hasLatinTitle
chosen
Indicates that an entity possesses a title or name expressed in Latin.
-
E.
usesColloquialCharacters
Indicates that an expression, name, or text is written using informal, non-standard, or colloquial characters rather than formal or standard script.
- 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_69c6884e15208190b9e91487eaafcf85 |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6e0c74fe48190aeaa018631e52ef6 |
completed | March 27, 2026, 7:55 p.m. |
| PD | Predicate disambiguation | batch_69c6d7bd5a388190a57a96d925696ff6 |
completed | March 27, 2026, 7:17 p.m. |
Created at: March 27, 2026, 2:27 p.m.