Triple
T756578
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Proto-Italic |
E15569
|
entity |
| Predicate | lexicalSimilarityWith |
P11829
|
FINISHED |
| Object | Proto-Celtic |
E4692
|
NE FINISHED |
How this triple was built (3 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: Proto-Celtic | Statement: [Proto-Italic, lexicalSimilarityWith, Proto-Celtic]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Proto-Celtic Context triple: [Proto-Italic, lexicalSimilarityWith, Proto-Celtic]
-
A.
Proto-Celtic
chosen
Proto-Celtic is the reconstructed common ancestor of the Celtic languages, spoken in prehistoric times before their diversification into distinct branches such as Goidelic and Brythonic.
-
B.
Proto-Goidelic
Proto-Goidelic is the reconstructed early Celtic language stage that gave rise to the Goidelic branch, including Primitive Irish and later Irish, Scottish Gaelic, and Manx.
-
C.
Proto-Indo-European
Proto-Indo-European is the reconstructed common ancestor of the vast Indo-European language family, from which many ancient and modern languages of Europe and Asia are derived.
-
D.
Proto-Germanic
Proto-Germanic is the reconstructed common ancestor of all Germanic languages, including English, German, and the Norse languages.
-
E.
Celtic languages
The Celtic languages are an ancient branch of the Indo-European language family once widespread across Europe, now represented mainly by languages such as Irish, Welsh, and Breton spoken in parts of the British Isles and Brittany.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lexicalSimilarityWith Context triple: [Proto-Italic, lexicalSimilarityWith, Proto-Celtic]
-
A.
hasLexicalSimilarityWith
chosen
Indicates that two linguistic items share a significant degree of similarity in form, structure, or wording.
-
B.
hasGrammaticalSimilarityTo
Indicates that two linguistic elements share similar grammatical structure, form, or function.
-
C.
hasPhonologicalSimilarityTo
Indicates that two linguistic elements share similar sound patterns or phonological features.
-
D.
linguisticallyRelatedTo
Indicates that two entities are connected through a linguistic relationship, such as sharing a common language, origin, structure, or other language-based association.
-
E.
usesRankStructureSimilarTo
Indicates that one entity organizes or orders its elements according to a ranking system that is similar to the ranking system used by another entity.
- F. None of above.
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_69a493599a0081908da65f3407af1ef2 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a66ab4608190afcd81e6606c5116 |
completed | March 1, 2026, 8:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a66d9764b081908f65c677582d9c86 |
completed | March 3, 2026, 5:11 a.m. |
| PD | Predicate disambiguation | batch_69a4a50348088190873a1446db657a78 |
completed | March 1, 2026, 8:43 p.m. |
Created at: March 1, 2026, 7:37 p.m.