Triple
T16376044
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yahya ibn Muhammad |
E397681
|
entity |
| Predicate | title |
P38
|
FINISHED |
| Object | Amir |
E66146
|
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: Amir | Statement: [Yahya ibn Muhammad, title, Amir]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Amir Context triple: [Yahya ibn Muhammad, title, Amir]
-
A.
Amir
chosen
Amir is a noble and military title historically used across the Islamic world, often denoting a commander, prince, or high-ranking leader.
-
B.
Amir
Amir is the conflicted Afghan protagonist of "The Kite Runner," whose journey is defined by childhood betrayal, guilt, and a quest for redemption.
-
C.
Sohrab
Sohrab is a tragic hero in the Persian epic Shahnameh, famed as the valiant but ill-fated son of the champion Rostam.
-
D.
Ali (The Kite Runner character)
Ali is a humble, loyal Hazara servant and childhood caretaker in The Kite Runner, known for his quiet dignity and deep bond with Baba’s family.
-
E.
Paul Amir
Paul Amir is a philanthropist and art patron known for his major support of cultural and architectural projects, including the Herta and Paul Amir Building.
- 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_69d87f2880b48190ae1a9673a3bbef80 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e319d79df8819087285b9457b7bdb6 |
completed | April 18, 2026, 5:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00356406208190a9cedc1de2ab4e07 |
completed | May 10, 2026, 7:36 a.m. |
Created at: April 10, 2026, 5:08 a.m.