Triple
T16058153
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cho Chang |
E389535
|
entity |
| Predicate | friend |
P8712
|
FINISHED |
| Object | Marietta Edgecombe |
E590470
|
NE 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: Marietta Edgecombe | Statement: [Cho Chang, friend, Marietta Edgecombe]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marietta Edgecombe Context triple: [Cho Chang, friend, Marietta Edgecombe]
-
A.
Marietta Edgecombe
chosen
Marietta Edgecombe is a Hogwarts student in the Harry Potter series who secretly informs Dolores Umbridge about Dumbledore’s Army, leading to the group’s exposure.
-
B.
Rebecca Chase
Rebecca Chase is a fictional character from the television series "NCIS," known primarily as one of Leroy Jethro Gibbs' ex-wives.
-
C.
Margaret Burr
Margaret Burr was the wife of renowned 18th-century English portrait and landscape painter Thomas Gainsborough and the mother of his two daughters.
-
D.
Martha Huggins
Martha Huggins is an actress best known for her role in the classic film "The Ghost and Mrs. Muir."
-
E.
Mary Ann Mobley
Mary Ann Mobley was an American actress, television personality, and former Miss America (1959) who appeared in numerous films and TV shows during the 1960s and 1970s.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d86dae698881908327ef2d67706cb9 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e1837634248190a99cc454ad1e99e0 |
completed | April 17, 2026, 12:48 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffe47a92608190993fe7f2c5957019 |
completed | May 10, 2026, 1:50 a.m. |
Created at: April 10, 2026, 4:57 a.m.