Triple
T32366405
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dwight McCarthy |
E827003
|
entity |
| Predicate | roleInOldTown |
P201793
|
FINISHED |
| Object | protector |
—
|
LITERAL 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: protector | Statement: [Dwight McCarthy, roleInOldTown, protector]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleInOldTown Context triple: [Dwight McCarthy, roleInOldTown, protector]
-
A.
oldTownCharacter
Indicates that something possesses the distinctive qualities or atmosphere typically associated with an old town.
-
B.
roleInNeverwhere
Indicates that one entity has a specific role or function within the context of "Neverwhere" in relation to another entity.
-
C.
roleInDarkCity
Indicates that an entity has a specific role, function, or character within the context of the work "Dark City."
-
D.
roleInRolandLife
Indicates that one entity holds a particular role or significance in the life or personal experience of Roland.
-
E.
fromTown
Indicates that one entity originates from, or is associated as being from, a particular town represented by the other entity.
- F. None of above. chosen
Provenance (4 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_69f349166d548190887b412fe908e2f4 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_6a002249ee388190a9501ee7630dc658 |
completed | May 10, 2026, 6:14 a.m. |
| PD | Predicate disambiguation | batch_6a002189273881909b6b687e2d61f5b1 |
completed | May 10, 2026, 6:11 a.m. |
| PDg | Predicate description generation | batch_6a0022494be881908bdf945d2393a40f |
completed | May 10, 2026, 6:14 a.m. |
Created at: May 1, 2026, 12:50 a.m.