Triple
T8367137
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Khaled al-Hassan |
E197155
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | al-Hassan |
E636939
|
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: al-Hassan | Statement: [Khaled al-Hassan, familyName, al-Hassan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: al-Hassan Context triple: [Khaled al-Hassan, familyName, al-Hassan]
-
A.
El Hajeb
El Hajeb is a town and provincial capital in northern Morocco, situated in the Fès-Meknès region.
-
B.
Dar Hussein
Dar Hussein is a historic palace in the Medina of Tunis, notable for its traditional Tunisian architecture and cultural significance.
-
C.
Hassan
Hassan is a loyal and selfless Hazara boy whose friendship with Amir and the injustices he endures form the emotional core of the film "The Kite Runner."
-
D.
Hassan
chosen
Hassan is a male given name of Arabic origin commonly used across the Muslim world and beyond.
-
E.
Hassan
Hassan is a person known primarily as the sibling of Murad Mirza.
- 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_69ca82f2dbe48190aba982e75a0d94de |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb808cf80c8190941c3cc0248a5df2 |
completed | March 31, 2026, 8:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cdc78c0c208190ba590c74512a4043 |
completed | April 2, 2026, 1:34 a.m. |
Created at: March 30, 2026, 6 p.m.