Triple
T29329106
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Philae |
E743729
|
entity |
| Predicate | firstSoftLandingOn |
P82944
|
FINISHED |
| Object | comet nucleus |
—
|
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: comet nucleus | Statement: [Philae, firstSoftLandingOn, comet nucleus]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstSoftLandingOn Context triple: [Philae, firstSoftLandingOn, comet nucleus]
-
A.
firstSoftLandingBy
chosen
Indicates that the subject is the first entity to successfully achieve a soft landing on the object.
-
B.
firstLandingAttemptOn
Indicates that an entity makes its initial attempt to land on another entity or location.
-
C.
firstLandingOutcome
Indicates the result or status that occurred from the initial landing event of an entity.
-
D.
firstLandingBy
Indicates that one entity is the earliest or initial instance to arrive, land, or touch down at a particular place or target relative to others.
-
E.
firstSuccessfulLander
Indicates that the subject entity is the earliest one to have successfully landed on the specified target or within the given context.
- 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_69f09125f784819080f4e9fce9fe624f |
completed | April 28, 2026, 10:51 a.m. |
| NER | Named-entity recognition | batch_6a00bcfed6448190b2e816bbe7c61c55 |
completed | May 10, 2026, 5:14 p.m. |
| PD | Predicate disambiguation | batch_6a00bc7be24c81908ba5c1957edd2c10 |
completed | May 10, 2026, 5:12 p.m. |
Created at: April 28, 2026, 1:28 p.m.