Triple
T32094815
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | the Blue Wizards |
E819697
|
entity |
| Predicate | companionsOnArrival |
P183317
|
FINISHED |
| Object | Gandalf |
—
|
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: Gandalf | Statement: [the Blue Wizards, companionsOnArrival, Gandalf]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: companionsOnArrival Context triple: [the Blue Wizards, companionsOnArrival, Gandalf]
-
A.
companionsCategory
Indicates that one entity is classified under a specific category related to companions or companionship.
-
B.
companionsDuringTreasureHunt
Indicates that two or more entities are companions accompanying each other during a treasure hunt activity.
-
C.
hasNumberOfCompanions
Indicates the quantity of companions or associates that an entity has.
-
D.
setCompanions
chosen
Indicates establishing or assigning one or more entities as companions to another entity, defining a companionship relationship between them.
-
E.
allegedCompanions
Indicates that two or more entities are claimed or reported to have been companions or associates, without confirming the truth of that relationship.
- 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_69f349004b2481908ce2e50af0d579a8 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69fbaebc8f2c8190b94f1b4a3ec92e8c |
completed | May 6, 2026, 9:12 p.m. |
| PD | Predicate disambiguation | batch_69fbadf1e6008190a71bbd196ba06844 |
completed | May 6, 2026, 9:09 p.m. |
Created at: May 1, 2026, 12:25 a.m.