Triple
T25006132
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Earl's Court (Neverwhere) |
E625844
|
entity |
| Predicate | usedByCharacters |
P31799
|
FINISHED |
| Object | Marquis de Carabas |
—
|
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: Marquis de Carabas | Statement: [Earl's Court (Neverwhere), usedByCharacters, Marquis de Carabas]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedByCharacters Context triple: [Earl's Court (Neverwhere), usedByCharacters, Marquis de Carabas]
-
A.
usedByCharacter
chosen
Indicates that something (such as an item, ability, or resource) is utilized or employed by a particular character.
-
B.
exploitedByCharacter
Indicates that a character takes unfair advantage of, manipulates, or otherwise uses another entity for their own benefit.
-
C.
wornByFictionalCharacter
Indicates that a particular item (such as clothing or accessories) is worn by a specific fictional character.
-
D.
ownedByFictionalCharacter
Indicates that something is possessed or owned by a fictional (not real-world) character.
-
E.
wasUsedBy
Indicates that something served as a tool, resource, or means for an agent to perform an action or achieve a result.
- F. None of above.
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_69e2ff26c50481908bc82e799c9e6587 |
completed | April 18, 2026, 3:48 a.m. |
| NER | Named-entity recognition | batch_69f497bc12b881908fe3386c66252bf6 |
completed | May 1, 2026, 12:08 p.m. |
| PD | Predicate disambiguation | batch_69f49366e8d08190adb4b71fe3a14683 |
completed | May 1, 2026, 11:49 a.m. |
Created at: April 18, 2026, 6:05 a.m.