Triple
T12668796
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Beverly Crusher |
E302623
|
entity |
| Predicate | closeTo |
P350
|
FINISHED |
| Object | Jean-Luc Picard |
E164059
|
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: Jean-Luc Picard | Statement: [Beverly Crusher, closeTo, Jean-Luc Picard]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jean-Luc Picard Context triple: [Beverly Crusher, closeTo, Jean-Luc Picard]
-
A.
Jean-Luc Picard
chosen
Jean-Luc Picard is the thoughtful and principled Starfleet captain of the USS Enterprise in the Star Trek franchise, known for his diplomacy, intellect, and moral leadership.
-
B.
Will Riker
Will Riker is a charismatic Starfleet officer best known as Captain Jean-Luc Picard’s trusted first officer aboard the USS Enterprise in the Star Trek franchise.
-
C.
Geordi La Forge
Geordi La Forge is a key Starfleet engineer in the Star Trek universe, best known as the visually impaired chief engineer of the USS Enterprise-D who uses a VISOR to see.
-
D.
Ian Andrew Troi
Ian Andrew Troi is the late Betazoid father of Starfleet counselor Deanna Troi in the Star Trek universe.
-
E.
Picard
Picard is a Romance language closely related to French, traditionally spoken in parts of northern France and southern Belgium.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d7bded71a88190bb76e2413af9ea66 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d96183a6048190b2ef219eb9d20aa4 |
completed | April 10, 2026, 8:45 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f684dfce0c8190b3b8260450bd6967 |
completed | May 2, 2026, 11:12 p.m. |
Created at: April 9, 2026, 5:20 p.m.