Triple
T22546391
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mort |
E557439
|
entity |
| Predicate | hasNotableBearer |
P458
|
FINISHED |
| Object |
Mort Castle
Mort Castle is an American horror author, editor, and writing teacher known for his dark fiction and contributions to contemporary horror literature.
|
E1541339
|
NE FINISHED |
How this triple was built (4 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: Mort Castle | Statement: [Mort, hasNotableBearer, Mort Castle]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mort Castle Context triple: [Mort, hasNotableBearer, Mort Castle]
-
A.
Mar Castle
Mar Castle is a historic Scottish stronghold in Aberdeenshire long associated with the Erskine family, former Earls of Mar.
-
B.
King’s Castle
King’s Castle is a historic coastal fortification in Bermuda that forms part of the UNESCO-listed defenses of the Town of St. George.
-
C.
Maurick Castle
Maurick Castle is a historic moated castle and estate near Vught in the Netherlands, known for its medieval origins and picturesque setting.
-
D.
Walzin Castle
Walzin Castle is a picturesque medieval fortress perched dramatically on a cliff above the Lesse River in the municipality of Houyet, Belgium.
-
E.
Roy's Castle
Roy's Castle is a fortress level in the Forest of Illusion world of Super Mario World, serving as the stronghold of the Koopaling Roy Koopa.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Mort Castle Triple: [Mort, hasNotableBearer, Mort Castle]
Generated description
Mort Castle is an American horror author, editor, and writing teacher known for his dark fiction and contributions to contemporary horror literature.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Mort Castle Target entity description: Mort Castle is an American horror author, editor, and writing teacher known for his dark fiction and contributions to contemporary horror literature.
-
A.
Mar Castle
Mar Castle is a historic Scottish stronghold in Aberdeenshire long associated with the Erskine family, former Earls of Mar.
-
B.
King’s Castle
King’s Castle is a historic coastal fortification in Bermuda that forms part of the UNESCO-listed defenses of the Town of St. George.
-
C.
Maurick Castle
Maurick Castle is a historic moated castle and estate near Vught in the Netherlands, known for its medieval origins and picturesque setting.
-
D.
Walzin Castle
Walzin Castle is a picturesque medieval fortress perched dramatically on a cliff above the Lesse River in the municipality of Houyet, Belgium.
-
E.
Roy's Castle
Roy's Castle is a fortress level in the Forest of Illusion world of Super Mario World, serving as the stronghold of the Koopaling Roy Koopa.
- F. None of above. chosen
Provenance (5 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_69e11e58662081909ae346ab384514ca |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15f35b9888190b4e1b50d5097b211 |
completed | April 29, 2026, 1:30 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0b1deaee088190a354d2b3f60fd07c |
completed | May 18, 2026, 2:10 p.m. |
| NEDg | Description generation | batch_6a0b1e7c4d648190990b698dd8ac5dbc |
completed | May 18, 2026, 2:13 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0b1efb36ac8190a4a9c3005ee58d23 |
completed | May 18, 2026, 2:15 p.m. |
Created at: April 16, 2026, 8:51 p.m.