Triple
T33464989
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Herbert Pocket |
E857020
|
entity |
| Predicate | firstMeetsPipAt |
P58222
|
FINISHED |
| Object | Satis House |
E1107031
|
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: Satis House | Statement: [Herbert Pocket, firstMeetsPipAt, Satis House]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstMeetsPipAt Context triple: [Herbert Pocket, firstMeetsPipAt, Satis House]
-
A.
firstMeets
chosen
Indicates that one entity encounters or comes into contact with another entity for the first time.
-
B.
firstAppearsAtLocation
Indicates the initial location where an entity is first observed, introduced, or comes into existence within a given context or sequence.
-
C.
firstTubeOpened
Indicates that the first tube in a sequence or system has been opened or activated.
-
D.
isOftenFirstPointSeenBy
Indicates that one entity is typically the initial point of contact or the first thing encountered by another entity.
-
E.
firstOccupied
Indicates that an entity was the initial or earliest occupant of a particular place, position, or resource.
- F. None of above.
Provenance (4 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_69f34973461481909c701c98ebd75623 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_6a037c8ae0248190b7e2ce4bf852c22d |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a3595a6cb48819092268845c3a08779 |
completed | June 19, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a0379f505c88190ac0879ab422c3054 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 1, 2026, 1:37 a.m.