Triple
T19985448
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | History of Magic |
E493919
|
entity |
| Predicate | firstYearOfferedTo |
P61242
|
FINISHED |
| Object | Hogwarts second-year students |
—
|
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: Hogwarts second-year students | Statement: [History of Magic, firstYearOfferedTo, Hogwarts second-year students]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstYearOfferedTo Context triple: [History of Magic, firstYearOfferedTo, Hogwarts second-year students]
-
A.
firstYear
Indicates that an entity is in its first year of existence, operation, or participation within a specified context.
-
B.
firstTaughtIn
chosen
Indicates the time or place at which something (such as a concept, subject, or course) was initially taught or introduced in an instructional context.
-
C.
firstArrivalYear
Indicates the calendar year in which an entity first arrived at or was initially present in a specified place or context.
-
D.
firstRunningYear
Indicates the year in which something (such as an event, service, or operation) first began running or was initially active.
-
E.
yearTaken
Indicates the specific calendar year in which an action, event, or record associated with the subject was carried out or occurred.
- 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_69da626a67648190af9653832a3aeced |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e65d162b008190a18d325796d75d77 |
completed | April 20, 2026, 5:06 p.m. |
| PD | Predicate disambiguation | batch_69e537fd311881908448f2aea8b4812e |
completed | April 19, 2026, 8:15 p.m. |
Created at: April 11, 2026, 3:29 p.m.