Triple
T8476135
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hugh Hudson |
E200397
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Maryam d'Abo |
E674764
|
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: Maryam d'Abo | Statement: [Hugh Hudson, spouse, Maryam d'Abo]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Maryam d'Abo Context triple: [Hugh Hudson, spouse, Maryam d'Abo]
-
A.
Maryam d'Abo
chosen
Maryam d'Abo is an English actress best known for playing Bond girl Kara Milovy in the James Bond film "The Living Daylights."
-
B.
Mariam Bai
Mariam Bai was a member of the prominent Jinnah family, historically notable in the context of South Asian politics and the creation of Pakistan.
-
C.
Maryam
Maryam is a revered figure in Islam, honored in the Qur’an as the mother of Prophet Isa (Jesus) and a model of piety and devotion.
-
D.
Askala Maryam
Askala Maryam was the birth name of Empress Zewditu I, the first female head of state of an internationally recognized African country and a ruler of Ethiopia in the early 20th century.
-
E.
Yasmina
Yasmina is the given first name of French actress Isabelle Adjani, reflecting her Algerian heritage.
- 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_69ca831b17988190a1f3f3413d57b820 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe51e21548190811e3c7ba7b196e5 |
completed | March 31, 2026, 3:15 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ce4de1fae48190a1149f639faca147 |
completed | April 2, 2026, 11:07 a.m. |
Created at: March 30, 2026, 6:12 p.m.