Triple
T20453433
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Player 001 |
E501712
|
entity |
| Predicate | relationshipToSeongGiHun |
P140158
|
FINISHED |
| Object | friend and game partner |
—
|
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: friend and game partner | Statement: [Player 001, relationshipToSeongGiHun, friend and game partner]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipToSeongGiHun Context triple: [Player 001, relationshipToSeongGiHun, friend and game partner]
-
A.
relationshipToHannah
Indicates the specific type of relationship or connection that an entity has to Hannah.
-
B.
relationshipToTheDude
Indicates the specific type of personal or social relationship that one entity has to the individual referred to as "the Dude."
-
C.
showsRelationshipWith
Indicates that one entity visually or explicitly presents or demonstrates its connection or association with another entity.
-
D.
relationshipToYukina
Indicates a specified type of personal or social connection that an entity has with Yukina.
-
E.
relationshipToJoni
Indicates the specific familial, social, or professional connection that one entity has to the person or entity named Joni.
- F. None of above. chosen
Provenance (4 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_69e0b4ac0a1c81908845d0f8a56abce8 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e68d039af08190827bf765b50515a8 |
completed | April 20, 2026, 8:30 p.m. |
| PD | Predicate disambiguation | batch_69e57679eb40819086142df3e39c928e |
completed | April 20, 2026, 12:42 a.m. |
| PDg | Predicate description generation | batch_69e58d766b408190a1d3698145fb6d30 |
completed | April 20, 2026, 2:20 a.m. |
Created at: April 16, 2026, 11:32 a.m.