Triple
T20109810
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Proto-Haida |
E490296
|
entity |
| Predicate | hasReconstructedLexicon |
P39028
|
FINISHED |
| Object | yes |
—
|
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: yes | Statement: [Proto-Haida, hasReconstructedLexicon, yes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasReconstructedLexicon Context triple: [Proto-Haida, hasReconstructedLexicon, yes]
-
A.
hasLexicalReconstruction
chosen
Indicates that there exists a hypothesized or reconstructed lexical form corresponding to a word or expression, typically inferred for an earlier or unattested stage of a language.
-
B.
hasLexicalReconstructionDomain
Indicates that something belongs to or is associated with a particular domain or scope within which its lexical reconstruction is defined or applicable.
-
C.
hasLexiconPreservedIn
Indicates that the lexicon of one entity is preserved, recorded, or stored within another entity.
-
D.
hasLexiconSource
Indicates that a lexical item or entry is derived from, documented in, or otherwise sourced from a particular lexicon or lexical resource.
-
E.
hasReconstructedFeatures
Indicates that certain features of an entity have been rebuilt, restored, or inferred from incomplete or damaged original data.
- F. None of above.
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_69da62636cc08190982cc71733a17b8d |
completed | April 11, 2026, 3:01 p.m. |
| NER | Named-entity recognition | batch_69e666df1b148190a28ead2f7cce7aab |
completed | April 20, 2026, 5:48 p.m. |
| PD | Predicate disambiguation | batch_69e54cf788188190a46cc49c9ce7617f |
completed | April 19, 2026, 9:45 p.m. |
Created at: April 11, 2026, 11:28 p.m.