Triple
T6162308
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Andrea Sachs |
E137469
|
entity |
| Predicate | friend |
P8712
|
FINISHED |
| Object | Doug |
E1851
|
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: Doug | Statement: [Andrea Sachs, friend, Doug]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Doug Context triple: [Andrea Sachs, friend, Doug]
-
A.
Doug
chosen
Doug is a common English masculine given name, typically used as a short form of Douglas.
-
B.
Dave
Dave is a common masculine given name, often a shortened form of David, used widely in English-speaking countries.
-
C.
Don
The Don is a major river in southwestern Russia that flows from the Central Russian Upland to the Sea of Azov, historically serving as an important trade route and cultural boundary.
-
D.
Don
Don is a masculine given name, often a short form of Donald, used in English-speaking countries.
-
E.
Dan
Dan is a character in the play "Clybourne Park," representing a contemporary figure who uncovers the neighborhood’s buried history and helps connect past events to present-day tensions.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69c008a54fc88190b6ce4416490ca79d |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c05d371484819090c18b62b095b49e |
completed | March 22, 2026, 9:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c14199f024819089af02b1c0eebfad |
completed | March 23, 2026, 1:35 p.m. |
Created at: March 22, 2026, 4:17 p.m.