Triple
T17362754
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Irene Hervey |
E422108
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Allan Jones |
—
|
NE ONNED1 |
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: Allan Jones | Statement: [Irene Hervey, spouse, Allan Jones]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Allan Jones Context triple: [Irene Hervey, spouse, Allan Jones]
-
A.
Allan Jones
chosen
Allan Jones was an American actor and tenor best known for his musical film roles in the 1930s, particularly in classic Marx Brothers comedies.
-
B.
Allan Nicholls
Allan Nicholls is an American actor, director, and musician best known for his collaborations with filmmaker Robert Altman in the 1970s.
-
C.
Allan Roberts
Allan Roberts was an American songwriter best known for co-writing popular standards and film music during the mid-20th century.
-
D.
Larry Buttrose
Larry Buttrose is an Australian writer and journalist known for his work across fiction, non-fiction, and screenwriting.
-
E.
Allan Little
Allan Little is a British journalist and former BBC correspondent known for his in-depth reporting on international conflicts and political affairs.
- 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_69d889d520008190a26917a95bf1c2ea |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e43a4e3c3481909dfaa00334c5010e |
completed | April 19, 2026, 2:13 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a01956294ec819083c1dde8fc2685e4 |
in_progress | May 11, 2026, 8:37 a.m. |
Created at: April 10, 2026, 5:44 a.m.