Triple
T16544195
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jane Skinner |
E401898
|
entity |
| Predicate | employer |
P7
|
FINISHED |
| Object | WCSH |
E809121
|
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: WCSH | Statement: [Jane Skinner, employer, WCSH]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: WCSH Context triple: [Jane Skinner, employer, WCSH]
-
A.
WCSH
chosen
WCSH is a television station serving the Portland, Maine market, known primarily as an NBC affiliate providing local news and network programming.
-
B.
WNSH
WNSH is a New York City-area radio station known for its country music format and association with major broadcasting networks.
-
C.
WUSN
WUSN is a Chicago-based country music radio station commonly known as "US*99."
-
D.
WHDH-TV
WHDH-TV is a Boston-based television station historically known as a major local news outlet and an early employer of prominent journalists such as Tom Brokaw.
-
E.
WCCB
WCCB is India’s specialized government agency responsible for combating wildlife-related crimes and enforcing laws to protect endangered species and their habitats.
- 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_69d88384bc30819084229e7dcdc39a41 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e34560daf08190b353b415d8ab280d |
completed | April 18, 2026, 8:48 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0067b3248c8190b63793bfc072aa4f |
completed | May 10, 2026, 11:10 a.m. |
Created at: April 10, 2026, 5:15 a.m.