Triple
T2860048
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Qusay Hussein |
E63296
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | Rana Hussein |
E298480
|
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: Rana Hussein | Statement: [Qusay Hussein, sibling, Rana Hussein]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rana Hussein Context triple: [Qusay Hussein, sibling, Rana Hussein]
-
A.
Rana Hussein
chosen
Rana Hussein is one of the daughters of former Iraqi president Saddam Hussein and his first wife, Sajida Talfah.
-
B.
Hany Mukhtar
Hany Mukhtar is a German professional soccer player and attacking midfielder known as a star playmaker and MVP-caliber performer for Nashville SC in Major League Soccer.
-
C.
Hussain Kirsha
Hussain Kirsha is a character in Naguib Mahfouz’s novel "Midaq Alley," known as the son of a café owner whose ambitions and moral compromises reflect the social changes in mid-20th-century Cairo.
-
D.
Hani Salaam
Hani Salaam is a high-ranking and sophisticated Jordanian intelligence chief featured in the espionage thriller "Body of Lies."
-
E.
Abdulla Elyas
Abdulla Elyas is a Saudi entrepreneur best known as one of the co-founders of the Middle Eastern ride-hailing company Careem.
- 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_69ab4c41e8c08190a9e8f5249cc12610 |
completed | March 6, 2026, 9:50 p.m. |
| NER | Named-entity recognition | batch_69abdf8aec3c8190a4168d8c916b5268 |
completed | March 7, 2026, 8:19 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b055e0c8088190a0fa67c9c14fc29b |
completed | March 10, 2026, 5:33 p.m. |
Created at: March 6, 2026, 10:02 p.m.