Triple
T15321478
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Alvin Kersh |
E366300
|
entity |
| Predicate | positionInFBI |
P118103
|
FINISHED |
| Object | Mulder and Scully's superior |
—
|
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: Mulder and Scully's superior | Statement: [Alvin Kersh, positionInFBI, Mulder and Scully's superior]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: positionInFBI Context triple: [Alvin Kersh, positionInFBI, Mulder and Scully's superior]
-
A.
joinsFBI
Indicates that an entity becomes a member of, or formally enters into service with, the FBI.
-
B.
professionBeforeFBI
Indicates that a person held a particular profession or job prior to joining or working for the FBI.
-
C.
positionOnCrime
Indicates a stance, opinion, or policy position that an entity holds regarding crime or crime-related issues.
-
D.
roleRelativeToFIA
Indicates the specific functional or organizational role an entity holds in relation to a designated FIA (e.g., as controller, participant, or associated party).
-
E.
roleInInterpol
Indicates that one entity holds or has held a specific role, position, or function within the organization Interpol in relation to 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_69d85a121520819093dcce999fdefe1a |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03dd460288190b5c41f0a0aeee949 |
completed | April 16, 2026, 1:39 a.m. |
| PD | Predicate disambiguation | batch_69deca9659f48190b8661df223ce5078 |
completed | April 14, 2026, 11:15 p.m. |
| PDg | Predicate description generation | batch_69decf2e413481909d9180a8d78d2c17 |
completed | April 14, 2026, 11:35 p.m. |
Created at: April 10, 2026, 3:16 a.m.