Triple
T3698434
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sentinelese language |
E78512
|
entity |
| Predicate | lexicon |
P42778
|
FINISHED |
| Object | unknown |
—
|
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: unknown | Statement: [Sentinelese language, lexicon, unknown]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lexicon Context triple: [Sentinelese language, lexicon, unknown]
-
A.
partOfLexicon
chosen
Indicates that a linguistic unit (such as a word or expression) belongs to or is included within a particular lexicon or vocabulary set.
-
B.
lexiconStatus
Indicates the current state or condition of a lexical item within a lexicon, such as whether it is active, deprecated, provisional, or otherwise classified.
-
C.
lexicalItem
Indicates that one entity is a word or vocabulary unit associated with, or used to express, another entity (such as a concept, meaning, or linguistic entry).
-
D.
sharesLexiconWith
Indicates that two entities use or are associated with the same set of lexical items, vocabulary, or word inventory.
-
E.
languageTerm
Indicates that one entity is a linguistic expression (word, phrase, or term) used to denote or label the other entity.
- 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_69ad85e3b1888190abc983e06968696d |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc512ba188190a15bcacafac3f476 |
completed | March 8, 2026, 6:50 p.m. |
| PD | Predicate disambiguation | batch_69adb84dc5808190850aa6975cb09e27 |
completed | March 8, 2026, 5:56 p.m. |
Created at: March 8, 2026, 3:26 p.m.