Triple
T14464481
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Carter |
E358670
|
entity |
| Predicate | starredActor |
P5563
|
FINISHED |
| Object | Lynn Collins |
E385331
|
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: Lynn Collins | Statement: [John Carter, starredActor, Lynn Collins]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lynn Collins Context triple: [John Carter, starredActor, Lynn Collins]
-
A.
Lynn Collins
chosen
Lynn Collins is an American actress known for her roles in films such as X-Men Origins: Wolverine and John Carter, as well as various television series.
-
B.
Melissa Cobb
Melissa Cobb is an American film producer best known for her work on major animated features, including the Kung Fu Panda franchise.
-
C.
Alice Patten
Alice Patten is a British actress best known internationally for her role as an English documentary filmmaker in the acclaimed Indian film "Rang De Basanti."
-
D.
Melissa Hudson
Melissa Hudson is known as the daughter of Stanley Hudson, a character from the American television series "The Office."
-
E.
Nicole Kassell
Nicole Kassell is an American film and television director and producer known for her work on acclaimed series such as Watchmen and The Leftovers.
- 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_69d827966698819082e140837737501d |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de91ad67bc81908ecdaa7262f6dc55 |
completed | April 14, 2026, 7:12 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69feadfaddc88190bb1196ace0bfd4ff |
completed | May 9, 2026, 3:46 a.m. |
Created at: April 10, 2026, 1:19 a.m.