Triple
T12585172
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1947 Roswell UFO incident |
E300436
|
entity |
| Predicate | hasHeadlineText |
P46191
|
FINISHED |
| Object | RAAF Captures Flying Saucer On Ranch in Roswell Region |
—
|
LITERAL 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: RAAF Captures Flying Saucer On Ranch in Roswell Region | Statement: [1947 Roswell UFO incident, hasHeadlineText, RAAF Captures Flying Saucer On Ranch in Roswell Region]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasHeadlineText Context triple: [1947 Roswell UFO incident, hasHeadlineText, RAAF Captures Flying Saucer On Ranch in Roswell Region]
-
A.
hasHeading
chosen
Indicates that one entity serves as a heading or title for another entity.
-
B.
hasText
Indicates that an entity is associated with or contains a specific piece of textual content.
-
C.
hasMastheadFeature
Indicates that one entity is highlighted or featured in the masthead section of another entity (such as a page, site, or publication).
-
D.
hasMainTitleCue
Indicates that an entity is associated with a primary or main title cue used for identification or display.
-
E.
hasPrimaryTitle
Indicates that an entity is associated with its main or official title, distinguishing it from any alternative or secondary titles.
- F. None of above.
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_69d7bde87b648190bcd0266e9efde098 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d954e6e20481908bca684c4b497c48 |
completed | April 10, 2026, 7:52 p.m. |
| PD | Predicate disambiguation | batch_69d95416cbd88190b2c65196162349bc |
completed | April 10, 2026, 7:48 p.m. |
Created at: April 9, 2026, 5:04 p.m.