Triple
T3554332
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Everybody Comes to Rick's |
E75182
|
entity |
| Predicate | author |
P4
|
FINISHED |
| Object | Joan Alison |
E148058
|
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: Joan Alison | Statement: [Everybody Comes to Rick's, author, Joan Alison]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Joan Alison Context triple: [Everybody Comes to Rick's, author, Joan Alison]
-
A.
Joan Alison
chosen
Joan Alison was an American screenwriter best known for co-writing the classic 1942 film "Casablanca."
-
B.
Joan Barclay
Joan Barclay was an American film actress known for her numerous roles in low-budget Westerns and B-movies during the 1930s and 1940s.
-
C.
Joan Murray
Joan Murray was the wife of famed British World War II flying ace and double amputee Sir Douglas Bader.
-
D.
Joan Felt
Joan Felt is the daughter of former FBI Associate Director and Watergate whistleblower Mark Felt, who later helped reveal his identity as "Deep Throat."
-
E.
Joan Rice
Joan Rice was a British film actress of the 1950s best known for her roles in adventure and comedy films produced by studios such as the Rank Organisation.
- 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_69ad85d33c6c819081d5ac1df13b5680 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc05549d88190acdebdd542ea1a67 |
completed | March 8, 2026, 6:30 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b4c3771e348190badb02264ecbdce2 |
completed | March 14, 2026, 2:09 a.m. |
Created at: March 8, 2026, 3:20 p.m.