Triple
T13109673
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mac |
E310936
|
entity |
| Predicate | friend |
P8712
|
FINISHED |
| Object | Dee Reynolds |
E220907
|
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: Dee Reynolds | Statement: [Mac, friend, Dee Reynolds]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dee Reynolds Context triple: [Mac, friend, Dee Reynolds]
-
A.
Dee Reynolds
chosen
Dee Reynolds is a main character on the TV show "It's Always Sunny in Philadelphia," known for her delusional aspirations, abrasive personality, and constant ridicule from the rest of the gang.
-
B.
Jane Reynolds
Jane Reynolds is a relatively obscure individual whose name is noted primarily as a recorded bearer of the Reynolds surname.
-
C.
Jeanie Drynan
Jeanie Drynan is an Australian actress best known for her film and television work, including a prominent role in the acclaimed comedy-drama "Muriel's Wedding."
-
D.
Nancy Susan Reynolds
Nancy Susan Reynolds was an American philanthropist and heiress of the R.J. Reynolds tobacco fortune, known for her extensive charitable work in education, the arts, and historic preservation.
-
E.
Debra Humphries
Debra Humphries is the mother of former NBA player Kris Humphries.
- 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_69d806a872d08190a329806f8ff30df4 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d9817e4f408190b77c198b4157d77a |
completed | April 10, 2026, 11:02 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fde158a5a48190b3945945f94f97a0 |
completed | May 8, 2026, 1:12 p.m. |
Created at: April 9, 2026, 9:05 p.m.