Triple
T18100230
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jake Sully |
E433193
|
entity |
| Predicate | speaks |
P741
|
FINISHED |
| Object | Na'vi language |
—
|
NE NERFINISHED |
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: Na'vi language | Statement: [Jake Sully, speaks, Na'vi language]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Na'vi language Context triple: [Jake Sully, speaks, Na'vi language]
-
A.
Naʼvi (constructed language)
chosen
Naʼvi is a constructed language created by linguist Paul Frommer for the fictional indigenous people in James Cameron’s film "Avatar," featuring its own grammar, vocabulary, and phonology.
-
B.
Kaera language
The Kaera language is a Papuan language spoken by a small community on Pantar Island in eastern Indonesia.
-
C.
Teiwa language
Teiwa language is a Papuan language spoken by the Teiwa people on Pantar Island in eastern Indonesia.
-
D.
Damara language
The Damara language is a Khoe (Central Khoisan) language spoken primarily by the Damara people of Namibia.
-
E.
Ahirani language
Ahirani language is an Indo-Aryan language spoken primarily in the Khandesh region of Maharashtra, India, known for its close relation to Marathi and distinct regional dialectal features.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b90916008190a1f110bd7ced5473 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4ddb5e6208190b3c3cce3b95d66ad |
completed | April 19, 2026, 1:50 p.m. |
Created at: April 10, 2026, 10:27 a.m.