Triple
T8889186
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gale Sondergaard |
E211620
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Gale |
E242733
|
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: Gale | Statement: [Gale Sondergaard, givenName, Gale]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gale Context triple: [Gale Sondergaard, givenName, Gale]
-
A.
Gale
chosen
Gale is a given name used for both males and females, historically associated with meanings related to strong winds or joviality.
-
B.
Gale
Gale is a research and educational publishing imprint known for providing digital archives, databases, and reference resources to libraries and academic institutions.
-
C.
Hayden
Hayden is a surname most notably associated with American actor and author Sterling Hayden, known for his roles in classic mid-20th-century films.
-
D.
Hayden
Hayden is a small city in northern Idaho, known for its proximity to Hayden Lake and its role as part of the Coeur d'Alene metropolitan area.
-
E.
Bramble
Bramble is a modern classic gin-based cocktail typically made with lemon juice, sugar syrup, and blackberry liqueur, served over crushed ice.
- 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_69ca83907954819096d52a245b635841 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc618f94108190b03248832bfe68a9 |
completed | April 1, 2026, 12:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfabe955e08190a8d61cfaa2d52731 |
completed | April 3, 2026, noon |
Created at: March 30, 2026, 6:53 p.m.