Triple
T8577591
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jon Davison |
E203085
|
entity |
| Predicate | employer |
P7
|
FINISHED |
| Object | IGN |
E481205
|
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: IGN | Statement: [Jon Davison, employer, IGN]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: IGN Context triple: [Jon Davison, employer, IGN]
-
A.
IGN
IGN is a French cartographic and geographic information agency best known for producing detailed maps and geographic data for France.
-
B.
IGN
IGN is the commonly used abbreviation for Spain’s Instituto Geográfico Nacional, the national authority responsible for official cartography, geodesy, and geographic information.
-
C.
IGN.com
IGN.com is a popular entertainment and gaming media website known for its news, reviews, and videos covering video games, movies, TV, and pop culture.
-
D.
IGN Entertainment
chosen
IGN Entertainment is a prominent online media company best known for its coverage of video games, entertainment, and pop culture through news, reviews, and multimedia content.
-
E.
Ing
Ing is a shortened form or nickname derived from the given name Ingrid.
- 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_69ca8328ebe481909a8c038fa79959b4 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbea989bec81909b8c8b4af7c568ff |
completed | March 31, 2026, 3:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ce899dd7d48190b44338b92ad68bd0 |
completed | April 2, 2026, 3:22 p.m. |
Created at: March 30, 2026, 6:22 p.m.