Triple
T29083127
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Annihilation: Conquest |
E734030
|
entity |
| Predicate | hasTieInSeries |
P20978
|
FINISHED |
| Object | Annihilation: Conquest – Star-Lord |
—
|
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: Annihilation: Conquest – Star-Lord | Statement: [Annihilation: Conquest, hasTieInSeries, Annihilation: Conquest – Star-Lord]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTieInSeries Context triple: [Annihilation: Conquest, hasTieInSeries, Annihilation: Conquest – Star-Lord]
-
A.
hasWorkInSameSeries
chosen
Indicates that two works belong to and are part of the same series.
-
B.
hasTiePossibility
Indicates that a situation, event, or interaction has the potential to end in a tie or draw rather than producing a single winner.
-
C.
hasBowlTieIn
Indicates that an entity is wearing or characterized by a bow tie in a particular context or situation.
-
D.
hasSiblingSeriesAppearance
Indicates that two entities appear as siblings within the same series or narrative work.
-
E.
airedWithSeriesUntil
Indicates that one series was broadcast together with another series up to a specified end point in time.
- 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_69f05b0c0f28819086eae6e84f2ae472 |
completed | April 28, 2026, 7 a.m. |
| NER | Named-entity recognition | batch_69f75dc25fa08190b371faf36d9fb72c |
completed | May 3, 2026, 2:37 p.m. |
| PD | Predicate disambiguation | batch_69f758586534819083e91172f4bf5098 |
completed | May 3, 2026, 2:14 p.m. |
Created at: April 28, 2026, 10:57 a.m.