Triple
T15211172
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Underground |
E363516
|
entity |
| Predicate | starredActor |
P5563
|
FINISHED |
| Object | Adina Porter |
E737513
|
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: Adina Porter | Statement: [Underground, starredActor, Adina Porter]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Adina Porter Context triple: [Underground, starredActor, Adina Porter]
-
A.
Adina Porter
chosen
Adina Porter is an American actress known for her powerful character roles in television series such as American Horror Story and True Blood.
-
B.
Audrey Purcell
Audrey Purcell is one of the children of actor Dominic Purcell, known for his role in the television series "Prison Break."
-
C.
Eugenia Perry
Eugenia Perry was the wife of famed Broadway producer David Merrick, known for her connection to his prominent theatrical career.
-
D.
Margot Pipkin
Margot Pipkin is a film producer known for her work on the animated feature "Mickey, Donald, Goofy: The Three Musketeers."
-
E.
Lydia Brazzi
Lydia Brazzi was the wife of Italian actor Rossano Brazzi, known primarily for her marriage to the internationally recognized film star.
- 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_69d85a0b78bc8190b6e5ad51a2c4cfc5 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e0076ad4ec81908d36f541fca08d72 |
completed | April 15, 2026, 9:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffa92b99c48190b76e1306cf32a568 |
completed | May 9, 2026, 9:37 p.m. |
Created at: April 10, 2026, 3:11 a.m.