Triple
T23372966
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lalla Rookh |
E593523
|
entity |
| Predicate | author |
P4
|
FINISHED |
| Object | Thomas Moore |
—
|
NE NERFINISHED |
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: Thomas Moore | Statement: [Lalla Rookh, author, Thomas Moore]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Thomas Moore Context triple: [Lalla Rookh, author, Thomas Moore]
-
A.
Thomas Moore
chosen
Thomas Moore was a renowned 19th-century Irish poet, singer, and songwriter best known for his lyrical verse and the collection "Irish Melodies."
-
B.
Thomas Moore
Thomas Moore is a fictional character appearing in the work titled "The Surgeon."
-
C.
Thomas Moore
Thomas Moore was an early settler and prominent landowner whose legacy is commemorated in the naming of Moorestown, New Jersey.
-
D.
Thomas Moore
Thomas Moore was an influential Anglican clergyman and philanthropist in Australia, best known for his role in establishing Moore Theological College in Sydney.
-
E.
John Benjamin Keane
John Benjamin Keane was a 19th-century Irish architect known for designing significant institutional buildings, including major works at Queen's College, Galway.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e25d268a50819095f2fd479da8ef3f |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1a3b0bc3c8190b1093f7ea29d015c |
completed | April 29, 2026, 6:22 a.m. |
Created at: April 17, 2026, 5:33 p.m.