Triple
T29804519
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Max (Good Boys) |
E756802
|
entity |
| Predicate | hasBestFriends |
P96345
|
FINISHED |
| Object | Lucas (Good Boys) |
—
|
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: Lucas (Good Boys) | Statement: [Max (Good Boys), hasBestFriends, Lucas (Good Boys)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasBestFriends Context triple: [Max (Good Boys), hasBestFriends, Lucas (Good Boys)]
-
A.
hasFriends
Indicates that an entity is socially connected to one or more other entities in a friendship relationship.
-
B.
hasGayBestFriend
Indicates that one entity has another entity as their closest friend, and that friend identifies as gay.
-
C.
hasYoungerFriend
Indicates that one person has a friend who is younger than they are.
-
D.
hasFriendship
Indicates a mutual, positive social relationship of friendship existing between two entities.
-
E.
bestFriendDynamicWith
chosen
Indicates a close, primary friendship relationship between two entities, typically characterized by mutual trust, support, and frequent positive interaction.
- 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_69f2245584848190ad4cab1f07752ccb |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69f72921cf2c8190909bb53f78bcc890 |
completed | May 3, 2026, 10:53 a.m. |
| PD | Predicate disambiguation | batch_69f7283d8cec8190b524c144948bc4ec |
completed | May 3, 2026, 10:49 a.m. |
Created at: April 29, 2026, 5:20 p.m.