Triple
T24149605
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nagan Kim clan |
E598490
|
entity |
| Predicate | hasClanMembers |
P7638
|
FINISHED |
| Object | people with the surname Kim whose bon-gwan is Nagan |
—
|
LITERAL 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: people with the surname Kim whose bon-gwan is Nagan | Statement: [Nagan Kim clan, hasClanMembers, people with the surname Kim whose bon-gwan is Nagan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasClanMembers Context triple: [Nagan Kim clan, hasClanMembers, people with the surname Kim whose bon-gwan is Nagan]
-
A.
hasMembers
chosen
Indicates that a group, organization, or collection includes certain entities as its members.
-
B.
hasTribalMembers
Indicates that a group, organization, or entity includes individuals who are recognized as members of a specific tribe.
-
C.
hasClanStatus
Indicates that an entity holds a specific role, rank, or membership status within a clan or clan-like group.
-
D.
hasClanOrBandStructure
Indicates that an entity is organized into, or participates in, a social structure based on clans or bands.
-
E.
hasTribalMembersFrom
Indicates that an entity includes or is composed of members originating from a specified tribe or tribal group.
- F. None of above.
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_69e288c9e488819093dd1acd91b08b8a |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f1e00e025c81908cacfcfa0819c73f |
completed | April 29, 2026, 10:40 a.m. |
| PD | Predicate disambiguation | batch_69f176585f3481909beb907de252cd98 |
completed | April 29, 2026, 3:09 a.m. |
Created at: April 17, 2026, 11:30 p.m.