Triple
T11439020
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Skip Donahue |
E271089
|
entity |
| Predicate | relationshipToHarryMonroe |
P99301
|
FINISHED |
| Object | 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: friend | Statement: [Skip Donahue, relationshipToHarryMonroe, friend]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipToHarryMonroe Context triple: [Skip Donahue, relationshipToHarryMonroe, friend]
-
A.
relationshipToHarryBright
Indicates that one entity has a specified personal or familial relationship to the person identified as Harry Bright.
-
B.
relationshipToHenry
Indicates the specific type of relationship or connection that an entity has to Henry.
-
C.
relationshipToHarveyCheyneJr
Indicates the specific familial, social, or professional relationship that an entity has to Harvey Cheyne Jr.
-
D.
relationshipToTony
Indicates the specific type of relationship or connection that an entity has with Tony.
-
E.
relationshipToJackBrown
Indicates the specific familial, social, or professional relationship that an entity has to Jack Brown.
- 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_69d6aadeef688190874bcecd88b3dd9b |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8088711ec8190afae9f4d9f2a11ca |
completed | April 9, 2026, 8:13 p.m. |
| PD | Predicate disambiguation | batch_69d7e7162b288190a0bfb89f7eb747c7 |
completed | April 9, 2026, 5:51 p.m. |
| PDg | Predicate description generation | batch_69d80010712c819089ea2e31e664abe1 |
completed | April 9, 2026, 7:37 p.m. |
Created at: April 8, 2026, 9:35 p.m.