Triple
T9152122
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sophie MacDonald |
E219610
|
entity |
| Predicate | relationshipTypeWith Larry Darrell |
P87042
|
FINISHED |
| Object | former childhood friend |
—
|
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: former childhood friend | Statement: [Sophie MacDonald, relationshipTypeWith Larry Darrell, former childhood friend]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipTypeWith Larry Darrell Context triple: [Sophie MacDonald, relationshipTypeWith Larry Darrell, former childhood friend]
-
A.
relationshipToLarryKeller
Indicates the specific type of relationship or connection an entity has to Larry Keller.
-
B.
relationshipToLaurie
Indicates the specific type of relationship or connection that an entity has to Laurie.
-
C.
relationshipTypeWith Alicia Johns
Indicates the specific type or nature of the relationship that an entity has with Alicia Johns.
-
D.
relationshipToLaureyWilliams
Indicates the nature or type of relational connection an entity has specifically to Laurey Williams.
-
E.
relationshipToTerry
Indicates the specific type of personal or social relationship that one entity has with Terry.
- 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_69ca83e25418819093c6503deeaf30de |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cca96cf4548190a3a45172f0e9d0ec |
completed | April 1, 2026, 5:13 a.m. |
| PD | Predicate disambiguation | batch_69cc6603ce8c8190bf6e8d6754bdec54 |
completed | April 1, 2026, 12:25 a.m. |
| PDg | Predicate description generation | batch_69cc6a3d230881909635b2ccea35cedb |
completed | April 1, 2026, 12:43 a.m. |
Created at: March 30, 2026, 7:20 p.m.