Triple
T11678698
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lydia |
E277557
|
entity |
| Predicate | screenplayBy |
P15305
|
FINISHED |
| Object | Zoe Akins |
E318253
|
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: Zoe Akins | Statement: [Lydia, screenplayBy, Zoe Akins]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Zoe Akins Context triple: [Lydia, screenplayBy, Zoe Akins]
-
A.
Zoe Akins
chosen
Zoe Akins was an American playwright, poet, and screenwriter best known for her sophisticated stage works and for becoming the first woman to win the Pulitzer Prize for Drama.
-
B.
Zoe Reynolds
Zoe Reynolds is a fictional MI5 intelligence officer and key member of the counter-terrorism team in the British television drama series "Spooks."
-
C.
Zoe Caldwell
Zoe Caldwell was an acclaimed Australian-born actress and four-time Tony Award winner, renowned for her powerful stage performances in both classical and contemporary roles.
-
D.
Zoe Barnes
Zoe Barnes is an ambitious and morally flexible young journalist in the political drama series "House of Cards."
-
E.
Zoe Buckman
Zoe Buckman is a British artist and photographer known for her feminist, multimedia works that explore themes of gender, sexuality, and power.
- 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_69d6aafd0a448190b44da30af8c6c519 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a46000a48190888ad1a6ade052e3 |
completed | April 10, 2026, 7:18 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ef82f515408190b21f1c7b207a2f0d |
completed | April 27, 2026, 3:38 p.m. |
Created at: April 8, 2026, 9:40 p.m.