Triple
T10821143
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saga |
E255371
|
entity |
| Predicate | mainCharacter |
P1183
|
FINISHED |
| Object | Alana |
E284352
|
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: Alana | Statement: [Saga, mainCharacter, Alana]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Alana Context triple: [Saga, mainCharacter, Alana]
-
A.
Alana
chosen
Alana is a feminine given name commonly used in English-speaking countries and various cultures worldwide.
-
B.
Elana
Elana is a Polish football club based in the city of Toruń.
-
C.
Annelise
Annelise is the given name of Anni Albers, the influential German-born textile artist and printmaker associated with the Bauhaus and later American modernism.
-
D.
Lana
Lana is a filmmaker best known as one of the Wachowski sisters, the co-creators of The Matrix film series.
-
E.
Lana
Lana is the seductive call girl who becomes the central love interest and catalyst for chaos in the 1983 film "Risky Business."
- 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_69d6aa8081448190a9324184f2bd1c26 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d73449eee88190afa52c4e6ef96baa |
completed | April 9, 2026, 5:08 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69de8578428c8190a25d9008881d0114 |
completed | April 14, 2026, 6:20 p.m. |
Created at: April 8, 2026, 9:18 p.m.