Triple
T8959871
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Naomie Harris |
E213973
|
entity |
| Predicate | portrayed |
P1668
|
FINISHED |
| Object | Tia Dalma |
E322828
|
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: Tia Dalma | Statement: [Naomie Harris, portrayed, Tia Dalma]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tia Dalma Context triple: [Naomie Harris, portrayed, Tia Dalma]
-
A.
Tia Dalma
chosen
Tia Dalma is a mysterious voodoo priestess and sea goddess in the Pirates of the Caribbean film series, known for her dark magic and deep connection to the ocean’s supernatural forces.
-
B.
Martika
Martika is an American pop singer and former child actress best known for her late-1980s hits like "Toy Soldiers."
-
C.
Dalida
Dalida was a hugely popular French-Italian-Egyptian singer and actress known for her multilingual hits and enduring influence on European and Middle Eastern pop music.
-
D.
Inna
Inna is a Romanian dance-pop singer known for international hits like "Hot" and "Sun Is Up."
-
E.
Denise Ream
Denise Ream is a film producer known for her work on major animated features, including Pixar's "Elemental."
- 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_69ca839cd6008190a1546a701a56710c |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc6746fbf88190aba658b4b9c2e4b0 |
completed | April 1, 2026, 12:31 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfc946a2f88190b7cd0fca67d31dfd |
completed | April 3, 2026, 2:05 p.m. |
Created at: March 30, 2026, 7 p.m.