Triple
T23446118
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | D.A. |
E565541
|
entity |
| Predicate | hasMember |
P10
|
FINISHED |
| Object | Michael Corner |
—
|
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: Michael Corner | Statement: [D.A., hasMember, Michael Corner]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michael Corner Context triple: [D.A., hasMember, Michael Corner]
-
A.
Michael Corner
chosen
Michael Corner is a minor character in the Harry Potter series, a Ravenclaw student who dates Ginny Weasley and later joins Dumbledore's Army.
-
B.
Chris Corner
Chris Corner is a British musician, singer, songwriter, and producer best known as the founder of the electronic project IAMX and former member of the trip-hop band Sneaker Pimps.
-
C.
Michael Harnett
Michael Harnett is the birth name of Michael Hartnett, a prominent Irish poet known for his lyrical work in both English and Irish.
-
D.
Michael Sayers
Michael Sayers was a screenwriter known for contributing to the script of the 1967 satirical James Bond film "Casino Royale."
-
E.
Mark Croft
Mark Croft is known as the husband of Australian actress Kerry Armstrong.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e24584f9488190bb32730bd2ce023e |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f1a64939e4819085862e7482e14879 |
completed | April 29, 2026, 6:33 a.m. |
Created at: April 17, 2026, 5:51 p.m.