Triple
T16697855
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | High Wall |
E405762
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Warner Anderson |
E493392
|
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: Warner Anderson | Statement: [High Wall, starring, Warner Anderson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Warner Anderson Context triple: [High Wall, starring, Warner Anderson]
-
A.
Warner Anderson
chosen
Warner Anderson was an American film and television actor active from the 1930s to the 1970s, known for his character roles in dramas and crime stories.
-
B.
Walt Anderson
Walt Anderson is a former NFL official who served as a longtime referee and later became the league’s senior vice president of officiating.
-
C.
Wilder Anderson
Wilder Anderson is a person known primarily for bearing the given name Wilder.
-
D.
Roy Anderson
Roy Anderson is a British epidemiologist and academic leader known for his influential work in infectious disease modeling and his tenure heading major scientific institutions.
-
E.
Roy Anderson
Roy Anderson is a fictional warehouse worker and former fiancé of Pam Beesly on the U.S. television series "The Office."
- 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_69d8838db21081909589220fd71440a4 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e3832e93c48190a594c498e9cc901a |
completed | April 18, 2026, 1:12 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0123257b908190819986393cb35748 |
completed | May 11, 2026, 12:30 a.m. |
Created at: April 10, 2026, 5:19 a.m.