Triple
T19155067
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dir |
E468908
|
entity |
| Predicate | usesClanName |
P68996
|
FINISHED |
| Object | Dir |
—
|
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: Dir | Statement: [Dir, usesClanName, Dir]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dir Context triple: [Dir, usesClanName, Dir]
-
A.
Dir
Dir is a town in Pakistan’s Khyber Pakhtunkhwa province, historically serving as a key gateway between the northern valleys and the Lowari Pass route to Chitral.
-
B.
Dir
chosen
Dir is one of the oldest and largest Somali clan families, historically influential across the Horn of Africa and central to Somali social and political structures.
-
C.
Director Q
Director Q is a music video director known for creating visually distinctive and stylistically innovative videos for various recording artists.
-
D.
Director K
Director K is a Nigerian music video director known for crafting visually striking videos for prominent Afrobeats artists.
-
E.
Ken Biller
Ken Biller is a television writer, producer, and director best known for his work on series such as "Star Trek: Voyager" and "Genius."
- 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_69d8dd084ff48190ac0f8c46ee722629 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5eeb914248190a92dc5f30cbc8fcc |
completed | April 20, 2026, 9:15 a.m. |
Created at: April 10, 2026, 12:06 p.m.