Triple
T9206033
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Umara ibn Hamza |
E220981
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Umara |
E220981
|
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: Umara | Statement: [Umara ibn Hamza, givenName, Umara]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Umara Context triple: [Umara ibn Hamza, givenName, Umara]
-
A.
Umara
Umara is the plural form of the Arabic name or title "Amir," commonly used to refer to multiple rulers or princes.
-
B.
Umara ibn Hamza
chosen
Umara ibn Hamza was an early Islamic figure known primarily as a descendant of the Prophet Muhammad’s uncle Hamza ibn Abd al-Muttalib.
-
C.
Hammad
Hammad is a character in the novel "Falling Man," which explores the aftermath of the September 11 attacks.
-
D.
Qasim
Qasim is a central character in Naguib Mahfouz’s novel "Children of Gebelawi," representing a modern, socially conscious figure modeled on the Prophet Muhammad within the book’s allegorical retelling of religious history.
-
E.
Abu al-Ula
Abu al-Ula was a Muslim ruler in medieval Seville under whose authority the iconic Torre del Oro was constructed.
- 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_69ca83e9d0e081908bdb71097201a06c |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69ccd947a0a08190966f22a6207c9120 |
completed | April 1, 2026, 8:37 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d077808ee48190be6b58a4b38f3e3d |
completed | April 4, 2026, 2:29 a.m. |
Created at: March 30, 2026, 7:26 p.m.