Triple
T20760379
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Habr Gedir |
E510961
|
entity |
| Predicate | hasSubclan |
P121811
|
FINISHED |
| Object | Saruur |
—
|
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: Saruur | Statement: [Habr Gedir, hasSubclan, Saruur]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Saruur Context triple: [Habr Gedir, hasSubclan, Saruur]
-
A.
Saruur
chosen
Saruur is a Somali sub-clan within the larger Hawiye clan-family, traditionally found in central and southern Somalia.
-
B.
Sarikoli
Sarikoli is an Eastern Iranian language spoken primarily by the Tajik ethnic community in the Tashkurgan region of Xinjiang, China.
-
C.
Sarachei
Sarachei is a small settlement located within the municipality of Kalampaka in the Thessaly region of Greece.
-
D.
Saratak
Saratak is a rural village located in Armenia's Shirak Province.
-
E.
Sa’luk
Sa’luk is a ruthless and treacherous member of the Forty Thieves who serves as the main villain in Disney’s animated film "Aladdin and the King of Thieves."
- 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_69e0b4c909ec8190b05987f1639513f6 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c248701081908ae49fca933e05f6 |
completed | April 21, 2026, 12:18 a.m. |
Created at: April 16, 2026, 12:35 p.m.