Triple
T10711156
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lucius Cornelius |
E252538
|
entity |
| Predicate | designed |
P184
|
FINISHED |
| Object | Tabularium |
E223938
|
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: Tabularium | Statement: [Lucius Cornelius, designed, Tabularium]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tabularium Context triple: [Lucius Cornelius, designed, Tabularium]
-
A.
Tabularium
chosen
The Tabularium was the official records office of ancient Rome, a monumental state archive building overlooking the Roman Forum.
-
B.
Tableau
Tableau is a widely used data visualization and business intelligence software platform that enables users to analyze, explore, and present data through interactive dashboards and reports.
-
C.
Tababela
Tababela is a rural parish in the Quito Metropolitan District of Ecuador, known for hosting the city’s main air gateway, Mariscal Sucre International Airport.
-
D.
Tabulahan
Tabulahan is a dialect of the Aralle-Tabulahan language spoken by a local community in West Sulawesi, Indonesia.
-
E.
Tabular Editor
Tabular Editor is a specialized development tool for creating, managing, and optimizing tabular models used in platforms like Azure Analysis Services and Power BI.
- 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_69d6aa5cbabc8190973e683950d89faf |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d6fe523de08190a82c8f057fe8baf6 |
completed | April 9, 2026, 1:18 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69dbb70f67c88190980f362fcea9d800 |
completed | April 12, 2026, 3:15 p.m. |
Created at: April 8, 2026, 9:13 p.m.