Triple
T21305653
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Juma bin Maktoum Al Maktoum |
E525191
|
entity |
| Predicate | nobleTitle |
P914
|
FINISHED |
| Object | Sheikh |
—
|
NE NERFINISHED |
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: Sheikh | Statement: [Juma bin Maktoum Al Maktoum, nobleTitle, Sheikh]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sheikh Context triple: [Juma bin Maktoum Al Maktoum, nobleTitle, Sheikh]
-
A.
Sheikh
chosen
Sheikh is an honorific title in Arabic-speaking and Islamic cultures denoting a leader, elder, or person of high social, religious, or political status.
-
B.
Sheikh Shams
Sheikh Shams is a central holy figure in Yazidism, often associated with the sun and revered as one of the key divine beings in the Yazidi religious tradition.
-
C.
Sheikh Taba
Sheikh Taba is a town located in the Akkar Governorate of northern Lebanon, near the border with Syria.
-
D.
Sheik
Sheik is the mysterious, ninja-like persona adopted by Princess Zelda in The Legend of Zelda series, known for agility, stealth, and guidance to the hero.
-
E.
al-Shaykh
al-Shaykh is an Arabic surname notably borne by Lebanese novelist and short story writer Hanan al-Shaykh.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b518b8948190ad69cf9a8784d397 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e75aa3f90481909b212bdbf00c2bb0 |
completed | April 21, 2026, 11:08 a.m. |
Created at: April 16, 2026, 4:05 p.m.