Triple
T18662221
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gurgi |
E456229
|
entity |
| Predicate | friendOf |
P8712
|
FINISHED |
| Object | Taran |
—
|
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: Taran | Statement: [Gurgi, friendOf, Taran]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Taran Context triple: [Gurgi, friendOf, Taran]
-
A.
Taran
chosen
Taran is the young, idealistic Assistant Pig-Keeper and main protagonist of Lloyd Alexander’s fantasy novel "The Black Cauldron," who dreams of becoming a great hero.
-
B.
Taran mac Ainftech
Taran mac Ainftech was a 7th-century king of the Picts in what is now Scotland, known primarily from early medieval king lists and chronicles.
-
C.
Taran Noah Smith
Taran Noah Smith is an American former child actor best known for playing youngest son Mark Taylor on the 1990s sitcom "Home Improvement."
-
D.
Taran Panth
Taran Panth is a reformist subsect of Digambara Jainism founded in the 16th century by Taran Svami, emphasizing scriptural study, inner devotion, and non-ritualistic worship.
-
E.
Arriel
Arriel is a family of turboshaft engines widely used in light and medium helicopters around the world.
- 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_69d8d38f72b4819090a935175d9ca8af |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e5508b35ec819085c1c4c2c98d6672 |
completed | April 19, 2026, 10 p.m. |
Created at: April 10, 2026, 11:48 a.m.