Triple
T16693970
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Taif |
E405666
|
entity |
| Predicate | commander |
P1061
|
FINISHED |
| Object | Muhammad |
E4752
|
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: Muhammad | Statement: [Battle of Taif, commander, Muhammad]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Muhammad Context triple: [Battle of Taif, commander, Muhammad]
-
A.
Muhammad
chosen
Muhammad is the 7th-century Arab religious, political, and social leader regarded by Muslims as the final prophet and messenger of God in Islam.
-
B.
Muhammad ibn al-Hanafiyyah
Muhammad ibn al-Hanafiyyah was a prominent early Islamic figure and son of Ali ibn Abi Talib, known for his piety, scholarship, and role in the political and theological developments following the early caliphates.
-
C.
Mohammad
Mohammad is the given first name of Indonesian independence leader and former vice president Bung Hatta.
-
D.
Mohammad
Mohammad is a common Arabic male given name, most notably borne by the Prophet of Islam and widely used across the Muslim world.
-
E.
Abu Hafs al-Hashimi al-Qurashi
Abu Hafs al-Hashimi al-Qurashi is a senior jihadist militant who has been identified as a leader within the Islamic State organization.
- 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_69d8838db21081909589220fd71440a4 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e37eab93a081909aedc45f3f8f0e10 |
completed | April 18, 2026, 12:52 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00919acd308190a3f29040554b9cfc |
completed | May 10, 2026, 2:09 p.m. |
Created at: April 10, 2026, 5:19 a.m.