Triple
T29799693
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Effie Deans |
E756657
|
entity |
| Predicate | relationshipToJeanieDeans |
P203627
|
FINISHED |
| Object | younger sister |
—
|
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: younger sister | Statement: [Effie Deans, relationshipToJeanieDeans, younger sister]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipToJeanieDeans Context triple: [Effie Deans, relationshipToJeanieDeans, younger sister]
-
A.
relationshipToJeanLundegaard
Indicates the specific familial, social, or professional relationship that one entity has to Jean Lundegaard.
-
B.
relationshipToEddieDean
Indicates the specific type of relationship or connection an entity has to Eddie Dean.
-
C.
relationshipToTinaBordereau
Indicates the specific type of personal or professional relationship an entity has with Tina Bordereau.
-
D.
relationshipToJeanValjean
Indicates the specific interpersonal or social connection that an entity has to Jean Valjean.
-
E.
relationshipTypeWithJanieCrawford
Indicates the specific nature or category of relationship that an entity has with Janie Crawford.
- 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_69f22454583081908927516cb9938d1d |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_6a01b841f5508190832bba00cf795bad |
completed | May 11, 2026, 11:06 a.m. |
| PD | Predicate disambiguation | batch_6a01b59541fc8190a9b13a55327c4aa1 |
completed | May 11, 2026, 10:55 a.m. |
| PDg | Predicate description generation | batch_6a01b8412624819086cf63e1b1f7eff1 |
completed | May 11, 2026, 11:06 a.m. |
Created at: April 29, 2026, 5:17 p.m.