Triple
T5325228
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Project-Based Voucher Program |
E121768
|
entity |
| Predicate | contractParty |
P52873
|
FINISHED |
| Object | public housing agency |
—
|
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: public housing agency | Statement: [Project-Based Voucher Program, contractParty, public housing agency]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: contractParty Context triple: [Project-Based Voucher Program, contractParty, public housing agency]
-
A.
negotiatingParty
Indicates that an entity is actively involved as a participant in a negotiation process with another entity.
-
B.
participatingParty
Indicates that an entity is involved as a participant in a particular event, activity, or transaction.
-
C.
nonSignatoryParty
Indicates that an entity is a party related to an agreement or treaty without having formally signed or acceded to it.
-
D.
arePartyTo
chosen
Indicates that the entities are participants or signatories in the same agreement, contract, or legal arrangement.
-
E.
otherSignificantParty
Indicates that an entity has another important associated party, such as a key counterpart, partner, or involved participant in a relationship or transaction.
- 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_69bd463d956c819088105c3db802c017 |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd86f20f008190be7b5848af05f2b8 |
completed | March 20, 2026, 5:42 p.m. |
| PD | Predicate disambiguation | batch_69bd84561c7081909e5937c7816e492c |
completed | March 20, 2026, 5:31 p.m. |
Created at: March 20, 2026, 1:59 p.m.