Triple
T36522604
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Susan Barnes |
E900215
|
entity |
| Predicate | heldRoleAt |
P37119
|
FINISHED |
| Object | NeXT |
—
|
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: NeXT | Statement: [Susan Barnes, heldRoleAt, NeXT]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: heldRoleAt Context triple: [Susan Barnes, heldRoleAt, NeXT]
-
A.
holdersPlayedRoleIn
Indicates that the holders of something (e.g., a position, title, or asset) participated in or contributed to a particular role within an event, activity, or context.
-
B.
servedInRole
chosen
Indicates that one entity performed duties or held a position within a specified role or office in relation to another entity.
-
C.
hasHistoricalRoleAs
Indicates that an entity has served in a specific historical capacity, function, or position during a particular period or context.
-
D.
leadershipRoleOn
Indicates that one entity holds a leadership position or role with respect to another entity.
-
E.
mayHavePriorRole
Indicates that an entity is allowed or expected to have held a specified role at some earlier time.
- 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_69f76e5eedb88190a393b8c623f71dd7 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7c371931c8190afb1d4dd5157f92c |
completed | May 3, 2026, 9:51 p.m. |
| PD | Predicate disambiguation | batch_69f7c1b91fd88190ab85afd626603769 |
completed | May 3, 2026, 9:44 p.m. |
Created at: May 3, 2026, 4:11 p.m.