Triple
T5214378
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zoe Saldana |
E117712
|
entity |
| Predicate | characterPortrayed |
P1507
|
FINISHED |
| Object | Neytiri |
E433194
|
NE 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: Neytiri | Statement: [Zoe Saldana, characterPortrayed, Neytiri]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Neytiri Context triple: [Zoe Saldana, characterPortrayed, Neytiri]
-
A.
Neytiri
chosen
Neytiri is a skilled Na'vi warrior and princess of the Omaticaya clan who becomes Jake Sully's guide and love interest in the film "Avatar."
-
B.
Shyriiwook
Shyriiwook is the guttural, roaring language spoken by the Wookiee species in the Star Wars universe.
-
C.
Marella
Marella is an Italian feminine given name, notably borne by Marella Agnelli, a prominent socialite, art collector, and style icon.
-
D.
Thargelion
Thargelion was a spring month in the ancient Attic calendar, roughly corresponding to parts of May and June in the modern Gregorian calendar.
-
E.
Yaviza
Yaviza is a small town in Panama’s Darién Province known as the southern terminus of the Pan-American Highway and a gateway to the remote Darién region.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69bd4464ba3c8190bc16b2ebbe42ddb0 |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd7a911d40819086621537274dc0f0 |
completed | March 20, 2026, 4:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69beefe325988190b35e3502f147c9c2 |
completed | March 21, 2026, 7:22 p.m. |
Created at: March 20, 2026, 1:47 p.m.