Triple
T17586574
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Edward Douglas |
E428336
|
entity |
| Predicate | alliesWith |
P435
|
FINISHED |
| Object | Aissa |
—
|
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: Aissa | Statement: [Edward Douglas, alliesWith, Aissa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Aissa Context triple: [Edward Douglas, alliesWith, Aissa]
-
A.
Aissa
Aissa is a central character in the 1996 film "The Island of Dr. Moreau," portrayed as a mysterious and compassionate human-animal hybrid who forms a crucial emotional connection with the protagonist.
-
B.
Aziza
Aziza is a traditional deity revered in Urhobo religion, associated with spiritual protection and guidance within the culture of the Urhobo people of Nigeria.
-
C.
Rachida
Rachida is a feminine given name of Arabic origin, notably borne by French politician Rachida Dati.
-
D.
Nafoua
Nafoua is a small settlement located on the remote Polynesian outlier island of Sikaiana in the Solomon Islands.
-
E.
Asmaa
Asmaa is a feminine given name of Arabic origin commonly used in many Muslim-majority countries.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide. chosen
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_69d889e1030481909950e140c63255b9 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e463d22f908190ae0f1eeafbe54459 |
completed | April 19, 2026, 5:10 a.m. |
Created at: April 10, 2026, 5:50 a.m.