Triple
T13346682
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Leah Lewis |
E317969
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Leah |
E44003
|
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: Leah | Statement: [Leah Lewis, givenName, Leah]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Leah Context triple: [Leah Lewis, givenName, Leah]
-
A.
Leah
Leah is a central character in the Diablo video game series, known as the ward of Deckard Cain who becomes pivotal to the conflict with the Prime Evils.
-
B.
Leah
chosen
Leah is a prominent biblical matriarch, wife of Jacob and mother of several tribes of Israel, traditionally believed to be buried in the Cave of the Patriarchs in Hebron.
-
C.
Leah
Leah is a song featured on Bruce Springsteen’s 2005 album "Devils & Dust."
-
D.
Leah Ray
Leah Ray was an American singer and film actress active in the 1930s, known for her musical performances in Hollywood productions.
-
E.
Lilah
Lilah is a feminine given name, often considered a modern, melodic variant of names like Lila or Delilah.
- 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_69d806b5a3c08190b42c267fb092f98a |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d99e89c65c819093f3bea11d6073c5 |
completed | April 11, 2026, 1:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f71f439b3c8190b35fd4d097d65068 |
completed | May 3, 2026, 10:11 a.m. |
Created at: April 9, 2026, 9:31 p.m.