Triple
T9259036
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | rubra |
E222523
|
entity |
| Predicate | lemma |
P87838
|
FINISHED |
| Object | ruber |
—
|
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: ruber | Statement: [rubra, lemma, ruber]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lemma Context triple: [rubra, lemma, ruber]
-
A.
legend
Indicates that an entity is a traditional or historical story, figure, or narrative widely regarded as legendary rather than strictly factual.
-
B.
statement
Indicates that an entity makes, issues, or expresses a declarative assertion, claim, or remark about something.
-
C.
premise
Indicates that a statement or proposition provides the foundational assumption or starting point from which a conclusion or inference is logically derived.
-
D.
proved
Indicates that one entity has demonstrated the truth or validity of another entity (such as a statement, theorem, or claim) through logical or evidential means.
-
E.
leverage
Indicates using something (such as a resource, asset, or advantage) to exert influence or gain a greater effect or benefit in a situation or relationship.
- F. None of above. chosen
Provenance (4 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_69ca841e4cd481908e738c74e958eaea |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd0714317481908405f857a4f49e74 |
completed | April 1, 2026, 11:52 a.m. |
| PD | Predicate disambiguation | batch_69cc7a4e79e48190b3200247f4624867 |
completed | April 1, 2026, 1:52 a.m. |
| PDg | Predicate description generation | batch_69cc95597be081908ece2491dd2f0f74 |
completed | April 1, 2026, 3:47 a.m. |
Created at: March 30, 2026, 7:32 p.m.