Triple
T37715950
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wiccan |
E939452
|
entity |
| Predicate | twinBrotherRealName |
P188963
|
FINISHED |
| Object | Thomas Shepherd |
E1848309
|
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: Thomas Shepherd | Statement: [Wiccan, twinBrotherRealName, Thomas Shepherd]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: twinBrotherRealName Context triple: [Wiccan, twinBrotherRealName, Thomas Shepherd]
-
A.
twinBrotherAlias
Indicates that one male individual is an alternate name or identity (alias) specifically for his twin brother.
-
B.
isFictionalTwinOf
Indicates that one entity is the imagined or fictional twin counterpart of another entity, typically within a narrative or creative context.
-
C.
halfBrotherAlias
Indicates that one entity is an alternative name or label used to refer to the half-brother of another entity.
-
D.
brotherNickname
Indicates that one person is known by a nickname specifically used by or associated with their brother.
-
E.
possibleBrother
Indicates a relationship where one entity may be the brother of another, but this has not been confirmed as certain.
- 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_69f76edc208c8190bc8b9683f75e1024 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fbaf48ba148190a8bdfd6846ad0540 |
completed | May 6, 2026, 9:14 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a40cdd7cb448190af6492d519179e34 |
completed | June 28, 2026, 7:31 a.m. |
| PD | Predicate disambiguation | batch_69fbadf632ec8190b14991c971258307 |
completed | May 6, 2026, 9:09 p.m. |
| PDg | Predicate description generation | batch_69fbaeef9c488190babb546b962b4fb6 |
completed | May 6, 2026, 9:13 p.m. |
Created at: May 3, 2026, 4:18 p.m.