Triple
T4148287
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Night Monster |
E89840
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Holmes Herbert |
E394463
|
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: Holmes Herbert | Statement: [Night Monster, starring, Holmes Herbert]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Holmes Herbert Context triple: [Night Monster, starring, Holmes Herbert]
-
A.
Frank Campion
Frank Campion is a Canadian municipal politician who serves as the mayor of Welland, Ontario.
-
B.
Cornelius Sherlock
Cornelius Sherlock was a British architect best known for designing prominent public buildings such as the Walker Art Gallery in Liverpool.
-
C.
Arthur Chesney
chosen
Arthur Chesney was a British actor known for his character roles in early 20th-century stage and film productions.
-
D.
Alfred Harker
Alfred Harker was a British geologist and petrologist renowned for his pioneering work on igneous rocks and the geology of the British Isles.
-
E.
Edward Holcroft
Edward Holcroft is a British actor known for his roles in film and television, including appearances in the Kingsman franchise and the series London Spy.
- 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_69aed95a59a881909b26e70b42c6811a |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69af02624a9c8190900e42e845ab7e4f |
completed | March 9, 2026, 5:24 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b57f3136c48190b158142311bfbc6d |
completed | March 14, 2026, 3:30 p.m. |
Created at: March 9, 2026, 3:43 p.m.