Triple
T5032240
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Light and Truth |
E113332
|
entity |
| Predicate | correspondsToLatinWord |
P60629
|
FINISHED |
| Object | Lux |
—
|
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: Lux | Statement: [Light and Truth, correspondsToLatinWord, Lux]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: correspondsToLatinWord Context triple: [Light and Truth, correspondsToLatinWord, Lux]
-
A.
correspondsToLatinLetter
Indicates that one entity is the counterpart or representation of another entity as a specific letter in the Latin alphabet.
-
B.
correspondsToEnglishLetter
Indicates that one entity is the English alphabet letter that matches, represents, or is equivalent to the other entity.
-
C.
linguisticallyRelatedTo
Indicates that two entities are connected through a linguistic relationship, such as sharing a common language, origin, structure, or other language-based association.
-
D.
cognateOf
Indicates that two linguistic forms share a common historical origin, typically descending from the same ancestral word.
-
E.
nameCognateOf
Indicates that two names share a common linguistic origin or form, typically due to derivation from the same root or historical source.
- 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_69bd443775e48190a646ffbfc4334723 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd73b4d1708190aa1fa63104555f8a |
completed | March 20, 2026, 4:20 p.m. |
| PD | Predicate disambiguation | batch_69bd71509e9c8190a60c1d8d04936a12 |
completed | March 20, 2026, 4:09 p.m. |
| PDg | Predicate description generation | batch_69bd724ff2b4819091351cf80d3647a1 |
completed | March 20, 2026, 4:14 p.m. |
Created at: March 20, 2026, 1:36 p.m.