Triple
T22504230
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zenith |
E556346
|
entity |
| Predicate | hasCompetitor |
P1375
|
FINISHED |
| Object | Starcom |
—
|
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: Starcom | Statement: [Zenith, hasCompetitor, Starcom]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Starcom Context triple: [Zenith, hasCompetitor, Starcom]
-
A.
Starcom
chosen
Starcom is a global media communications agency known for planning and buying advertising across multiple channels as part of the Publicis Groupe network.
-
B.
STARCOM
STARCOM is the United States Space Force field command responsible for training, education, doctrine, and test and evaluation for space forces.
-
C.
Sabrang Communications
Sabrang Communications is an Indian media and advocacy organization known for its work on human rights, communalism, and social justice issues.
-
D.
Stone Communications
Stone Communications is a public relations and political consulting firm associated with Republican strategist Roger Stone.
-
E.
Orbiscom
Orbiscom is a financial technology company best known for pioneering secure online payment and virtual card number solutions before being acquired by Mastercard.
- 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_69e11e555edc81909ca803587dafd747 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15d5ac5808190a66f9111c350f4dc |
completed | April 29, 2026, 1:22 a.m. |
Created at: April 16, 2026, 8:50 p.m.