Triple
T14080074
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Woman King |
E338841
|
entity |
| Predicate | portrays |
P264
|
FINISHED |
| Object | Nanisca |
E1077051
|
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: Nanisca | Statement: [The Woman King, portrays, Nanisca]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nanisca Context triple: [The Woman King, portrays, Nanisca]
-
A.
Nanisca
chosen
Nanisca is a fierce and strategic general of the all-female Agojie warriors in the historical epic film "The Woman King."
-
B.
Henoko
Henoko is a coastal district in Nago, Okinawa, Japan, known as a focal point of controversy over the planned relocation and expansion of U.S. military facilities.
-
C.
Niúachi
Niúachi is an alternative name for the Missouria, a Native American tribe historically located in the central United States along the Missouri River.
-
D.
Marisus
Marisus is the historical Latin name for the Mureș River, a major waterway flowing through present-day Romania and Hungary.
-
E.
Yoriko
Yoriko is a Japanese feminine given name commonly borne by women and girls in Japan.
- 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_69d81c687b0c819087fd9ed4198403f8 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de5c5f759c81909bfd60ab35b0937b |
completed | April 14, 2026, 3:25 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fcd0a175a48190b596ea4cf917e80e |
completed | May 7, 2026, 5:49 p.m. |
Created at: April 9, 2026, 10:21 p.m.