Triple
T38048759
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dr. Alexandre Manette |
E949694
|
entity |
| Predicate | firstSeenAt |
P18472
|
FINISHED |
| Object | Defarges’ wine shop in Paris |
E1315503
|
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: Defarges’ wine shop in Paris | Statement: [Dr. Alexandre Manette, firstSeenAt, Defarges’ wine shop in Paris]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstSeenAt Context triple: [Dr. Alexandre Manette, firstSeenAt, Defarges’ wine shop in Paris]
-
A.
firstUsedAt
Indicates the time or place at which something was initially used or put into operation.
-
B.
firstDetectedOn
Indicates the date or time when something was initially observed, discovered, or recorded for the first time.
-
C.
firstReachedDate
Indicates the date on which a particular entity first achieved, accessed, or arrived at a specified state, location, or milestone.
-
D.
firstAppearedAt
chosen
Indicates the point in time or specific event at which an entity was first introduced, observed, or became known.
-
E.
firstCreatedAt
Indicates the time or date at which an entity was initially created for the first time.
- 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_69f76f000cf081908c11fb5443b392e6 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_6a037df1223c8190a5d61e4f8e6fd613 |
completed | May 12, 2026, 7:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a41544f75a881909064467423fb21e7 |
completed | June 28, 2026, 5:05 p.m. |
| PD | Predicate disambiguation | batch_6a037a1ad6c48190bfe35d350c1b4751 |
completed | May 12, 2026, 7:06 p.m. |
Created at: May 3, 2026, 4:20 p.m.