Triple
T9129559
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Veritas et Libertas |
E219047
|
entity |
| Predicate | hasComponentWord |
P35
|
FINISHED |
| Object | Veritas |
E104
|
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: Veritas | Statement: [Veritas et Libertas, hasComponentWord, Veritas]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Veritas Context triple: [Veritas et Libertas, hasComponentWord, Veritas]
-
A.
Veritas
chosen
Veritas is the Latin word for "truth" and is famously used as the motto of Harvard University.
-
B.
Vartan
Vartan is a surname most notably associated with French-American actor Michael Vartan.
-
C.
Verus
Verus was the cognomen of Marcus Annius Verus, a Roman praetor and member of a prominent senatorial family in the 2nd century AD.
-
D.
Siris
Siris is a philosophical work by George Berkeley that explores metaphysics, theology, and the medicinal virtues of tar-water through a chain of reflective questions and arguments.
-
E.
Verily
Verily is a life sciences and healthcare technology company under Alphabet Inc. that focuses on using data and advanced tools to improve health outcomes.
- 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_69ca83debfc0819095800583e97ab10f |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cca8cdafb48190be5e62b15779d771 |
completed | April 1, 2026, 5:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d030a934988190976aa359f9f902c3 |
completed | April 3, 2026, 9:27 p.m. |
Created at: March 30, 2026, 7:18 p.m.