Triple
T17388005
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marlena Evans |
E422738
|
entity |
| Predicate | network |
P2637
|
FINISHED |
| Object | Peacock |
—
|
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: Peacock | Statement: [Marlena Evans, network, Peacock]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Peacock Context triple: [Marlena Evans, network, Peacock]
-
A.
Peacock
chosen
Peacock is a U.S.-based streaming service offering on-demand and live content, including NBC shows, Universal films, originals, news, and sports.
-
B.
Peacocks
The Peacocks are the athletic teams representing Saint Peter's University in intercollegiate sports.
-
C.
Pavo
Pavo is a genus of large, colorful birds in the pheasant family that includes the well-known peafowls.
-
D.
Pavo
Pavo is a small southern constellation named after the peacock, notable for its bright blue star Peacock (Alpha Pavonis) and rich fields of star clusters.
-
E.
Peah
Peah is a tractate of the Mishnah that outlines the agricultural gifts and portions of produce that must be left for the poor.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d889d710288190bf0f4762801fefae |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e43a8b66288190b29bb82eff761902 |
completed | April 19, 2026, 2:14 a.m. |
Created at: April 10, 2026, 5:45 a.m.