Triple
T19108681
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sergeant Quirt |
E467729
|
entity |
| Predicate | relationshipWithCaptainFlagg |
P132194
|
FINISHED |
| Object | friend |
—
|
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: friend | Statement: [Sergeant Quirt, relationshipWithCaptainFlagg, friend]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipWithCaptainFlagg Context triple: [Sergeant Quirt, relationshipWithCaptainFlagg, friend]
-
A.
relationshipToCaptain
chosen
Indicates the specific familial, professional, or social relationship that an entity has to a captain.
-
B.
laterCaptain
Indicates that one entity becomes the captain of something at a later time than another referenced captain or captaincy.
-
C.
relationshipWithKateBeckett
Indicates that there exists a personal or professional relationship involving Kate Beckett and another entity.
-
D.
captain
Indicates that one entity serves as the leader or person in command of another entity, typically a team, group, or vessel.
-
E.
relationshipStatusWithJackSparrow
Indicates the type or state of a subject’s personal relationship with Jack Sparrow.
- 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_69d8dd06a26481908039e2a1bae8c597 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5e391f00c8190881a5977dd3728ed |
completed | April 20, 2026, 8:28 a.m. |
| PD | Predicate disambiguation | batch_69e4b9ac41848190afd0f33b42cebe99 |
completed | April 19, 2026, 11:17 a.m. |
Created at: April 10, 2026, 12:04 p.m.